scholarly journals Compressed Wavelet Tensor Attention Capsule Network

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Xiushan Liu ◽  
Chun Shan ◽  
Qin Zhang ◽  
Jun Cheng ◽  
Peng Xu
Keyword(s):  
Neural Network ◽  
Frequency Domain ◽  
Wavelet Decomposition ◽  
State Of The Art ◽  
Texture Classification ◽  
Texture Features ◽  
Edge Computing ◽  
Spectral Features ◽  
Classification Methods ◽  
Classification Tasks

Texture classification plays an important role for various computer vision tasks. Depending upon the powerful feature extraction capability, convolutional neural network (CNN)-based texture classification methods have attracted extensive attention. However, there still exist many challenges, such as the extraction of multilevel texture features and the exploration of multidirectional relationships. To address the problem, this paper proposes the compressed wavelet tensor attention capsule network (CWTACapsNet), which integrates multiscale wavelet decomposition, tensor attention blocks, and quantization techniques into the framework of capsule neural network. Specifically, the multilevel wavelet decomposition is in charge of extracting multiscale spectral features in frequency domain; in addition, the tensor attention blocks explore the multidimensional dependencies of convolutional feature channels, and the quantization techniques make the computational storage complexities be suitable for edge computing requirements. The proposed CWTACapsNet provides an efficient way to explore spatial domain features, frequency domain features, and their dependencies which are useful for most texture classification tasks. Furthermore, CWTACapsNet benefits from quantization techniques and is suitable for edge computing applications. Experimental results on several texture datasets show that the proposed CWTACapsNet outperforms the state-of-the-art texture classification methods not only in accuracy but also in robustness.

scholarly journals Multi-Channel Convolutional Neural Networks Architecture Feeding for Effective EEG Mental Tasks Classification

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3451 ◽  
Author(s):  
Sławomir Opałka ◽  
Bartłomiej Stasiak ◽  
Dominik Szajerman ◽  
Adam Wojciechowski
Keyword(s):  
Neural Network ◽  
Frequency Domain ◽  
Classification Accuracy ◽  
State Of The Art ◽  
Parameters Optimization ◽  
Alternative Methods ◽  
Signal Frequency ◽  
Eeg Signal ◽  
Mental Tasks Classification ◽  
Mental Tasks

Mental tasks classification is increasingly recognized as a major challenge in the field of EEG signal processing and analysis. State-of-the-art approaches face the issue of spatially unstable structure of highly noised EEG signals. To address this problem, this paper presents a multi-channel convolutional neural network architecture with adaptively optimized parameters. Our solution outperforms alternative methods in terms of classification accuracy of mental tasks (imagination of hand movements and speech sounds generation) while providing high generalization capability (∼5%). Classification efficiency was obtained by using a frequency-domain multi-channel neural network feeding scheme by EEG signal frequency sub-bands analysis and architecture supporting feature mapping with two subsequent convolutional layers terminated with a fully connected layer. For dataset V from BCI Competition III, the method achieved an average classification accuracy level of nearly 70%, outperforming alternative methods. The solution presented applies a frequency domain for input data processed by a multi-channel architecture that isolates frequency sub-bands in time windows, which enables multi-class signal classification that is highly generalizable and more accurate (∼1.2%) than the existing solutions. Such an approach, combined with an appropriate learning strategy and parameters optimization, adapted to signal characteristics, outperforms reference single- or multi-channel networks, such as AlexNet, VGG-16 and Cecotti’s multi-channel NN. With the classification accuracy improvement of 1.2%, our solution is a clear advance as compared to the top three state-of-the-art methods, which achieved the result of no more than 0.3%.

Spectral features based convolutional neural network for accurate and prompt identification of schizophrenic patients

2020 ◽  
pp. 095441192096693
Author(s):  
Kuldeep Singh ◽  
Sukhjeet Singh ◽  
Jyoteesh Malhotra
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Frequency Domain ◽  
Short Term Memory ◽  
Spectral Power ◽  
Machine Learning Techniques ◽  
Spectral Amplitude ◽  
Spectral Features ◽  
Eeg Signals ◽  
Schizophrenic Patients

Schizophrenia is a fatal mental disorder, which affects millions of people globally by the disturbance in their thinking, feeling and behaviour. In the age of the internet of things assisted with cloud computing and machine learning techniques, the computer-aided diagnosis of schizophrenia is essentially required to provide its patients with an opportunity to own a better quality of life. In this context, the present paper proposes a spectral features based convolutional neural network (CNN) model for accurate identification of schizophrenic patients using spectral analysis of multichannel EEG signals in real-time. This model processes acquired EEG signals with filtering, segmentation and conversion into frequency domain. Then, given frequency domain segments are divided into six distinct spectral bands like delta, theta-1, theta-2, alpha, beta and gamma. The spectral features including mean spectral amplitude, spectral power and Hjorth descriptors (Activity, Mobility and Complexity) are extracted from each band. These features are independently fed to the proposed spectral features-based CNN and long short-term memory network (LSTM) models for classification. This work also makes use of raw time-domain and frequency-domain EEG segments for classification using temporal CNN and spectral CNN models of same architectures respectively. The overall analysis of simulation results of all models exhibits that the proposed spectral features based CNN model is an efficient technique for accurate and prompt identification of schizophrenic patients among healthy individuals with average classification accuracies of 94.08% and 98.56% for two different datasets with optimally small classification time.

scholarly journals A Lightweight Spectral–Spatial Feature Extraction and Fusion Network for Hyperspectral Image Classification

2020 ◽  
Vol 12 (9) ◽  
pp. 1395
Author(s):  
Linlin Chen ◽  
Zhihui Wei ◽  
Yang Xu
Keyword(s):  
Classification Accuracy ◽  
Hyperspectral Image ◽  
State Of The Art ◽  
Spectral Features ◽  
Classification Methods ◽  
Hyperspectral Image Classification ◽  
Spatial Feature ◽  
Deep Network ◽  
Spatial Features ◽  
Reduced Parameters

Hyperspectral image (HSI) classification accuracy has been greatly improved by employing deep learning. The current research mainly focuses on how to build a deep network to improve the accuracy. However, these networks tend to be more complex and have more parameters, which makes the model difficult to train and easy to overfit. Therefore, we present a lightweight deep convolutional neural network (CNN) model called S2FEF-CNN. In this model, three S2FEF blocks are used for the joint spectral–spatial features extraction. Each S2FEF block uses 1D spectral convolution to extract spectral features and 2D spatial convolution to extract spatial features, respectively, and then fuses spectral and spatial features by multiplication. Instead of using the full connected layer, two pooling layers follow three blocks for dimension reduction, which further reduces the training parameters. We compared our method with some state-of-the-art HSI classification methods based on deep network on three commonly used hyperspectral datasets. The results show that our network can achieve a comparable classification accuracy with significantly reduced parameters compared to the above deep networks, which reflects its potential advantages in HSI classification.

scholarly journals Regularized Chained Deep Neural Network Classifier for Multiple Annotators

2021 ◽  
Vol 11 (12) ◽  
pp. 5409
Author(s):  
Julián Gil-González ◽  
Andrés Valencia-Duque ◽  
Andrés Álvarez-Meza ◽  
Álvaro Orozco-Gutiérrez ◽  
Andrea García-Moreno
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Feature Space ◽  
Ground Truth ◽  
Amazon Mechanical Turk ◽  
Input Feature ◽  
Multiple Annotators ◽  
Classification Tasks ◽  
Multiple Experts

The increasing popularity of crowdsourcing platforms, i.e., Amazon Mechanical Turk, changes how datasets for supervised learning are built. In these cases, instead of having datasets labeled by one source (which is supposed to be an expert who provided the absolute gold standard), databases holding multiple annotators are provided. However, most state-of-the-art methods devoted to learning from multiple experts assume that the labeler’s behavior is homogeneous across the input feature space. Besides, independence constraints are imposed on annotators’ outputs. This paper presents a regularized chained deep neural network to deal with classification tasks from multiple annotators. The introduced method, termed RCDNN, jointly predicts the ground truth label and the annotators’ performance from input space samples. In turn, RCDNN codes interdependencies among the experts by analyzing the layers’ weights and includes l1, l2, and Monte-Carlo Dropout-based regularizers to deal with the over-fitting issue in deep learning models. Obtained results (using both simulated and real-world annotators) demonstrate that RCDNN can deal with multi-labelers scenarios for classification tasks, defeating state-of-the-art techniques.

scholarly journals A Self-Activated CNN Approach for Multi-Class Chest-Related COVID-19 Detection

2021 ◽  
Vol 11 (19) ◽  
pp. 9023
Author(s):  
Najam-ur Rehman ◽  
Muhammad Sultan Zia ◽  
Talha Meraj ◽  
Hafiz Tayyab Rauf ◽  
Robertas Damaševičius ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
State Of The Art ◽  
Detection System ◽  
Classification Methods ◽  
Single Class ◽  
X Ray ◽  
Computer Aided ◽  
Chest X Ray ◽  
Fully Connected

Chest diseases can be dangerous and deadly. They include many chest infections such as pneumonia, asthma, edema, and, lately, COVID-19. COVID-19 has many similar symptoms compared to pneumonia, such as breathing hardness and chest burden. However, it is a challenging task to differentiate COVID-19 from other chest diseases. Several related studies proposed a computer-aided COVID-19 detection system for the single-class COVID-19 detection, which may be misleading due to similar symptoms of other chest diseases. This paper proposes a framework for the detection of 15 types of chest diseases, including the COVID-19 disease, via a chest X-ray modality. Two-way classification is performed in proposed Framework. First, a deep learning-based convolutional neural network (CNN) architecture with a soft-max classifier is proposed. Second, transfer learning is applied using fully-connected layer of proposed CNN that extracted deep features. The deep features are fed to the classical Machine Learning (ML) classification methods. However, the proposed framework improves the accuracy for COVID-19 detection and increases the predictability rates for other chest diseases. The experimental results show that the proposed framework, when compared to other state-of-the-art models for diagnosing COVID-19 and other chest diseases, is more robust, and the results are promising.

scholarly journals A New Attention Mechanism to Classify Multivariate Time Series

2020 ◽  
Author(s):  
Yifan Hao ◽  
Huiping Cao
Keyword(s):  
Neural Network ◽  
Time Series ◽  
State Of The Art ◽  
Multivariate Time Series ◽  
Attention Mechanism ◽  
Classification Methods ◽  
Short Term ◽  
Time Step ◽  
Relevant Variables ◽  
Multiple Variables

Classifying multivariate time series (MTS), which record the values of multiple variables over a continuous period of time, has gained a lot of attention. However, existing techniques suffer from two major issues. First, the long-range dependencies of the time-series sequences are not well captured. Second, the interactions of multiple variables are generally not represented in features. To address these aforementioned issues, we propose a novel Cross Attention Stabilized Fully Convolutional Neural Network (CA-SFCN) to classify MTS data. First, we introduce a temporal attention mechanism to extract long- and short-term memories across all time steps. Second, variable attention is designed to select relevant variables at each time step. CA-SFCN is compared with 16 approaches using 14 different MTS datasets. The extensive experimental results show that the CA-SFCN outperforms state-of-the-art classification methods, and the cross attention mechanism achieves better performance than other attention mechanisms.

Ovarian Tumor Texture Classification Based on Sparse Auto-Encoder Network Combined with Multi-Feature Fusion and Random Forest in Ultrasound Image

2021 ◽  
Vol 11 (2) ◽  
pp. 424-431
Author(s):  
Yingxin Wang ◽  
Qianqian Zeng
Keyword(s):  
Neural Network ◽  
Feature Fusion ◽  
Texture Classification ◽  
Ultrasound Image ◽  
Texture Features ◽  
Recall Rate ◽  
Svm Classifier ◽  
Ultrasound Images ◽  
Feature Extraction Method

Texture analysis has always been active areas of ultrasound image processing research. Using texture features to classify the ultrasound images is the focus of researchers' attention. How to extract representative texture features is an important part of successful texture description. The research goal of this paper is to apply the deep neural network into the ultrasound classification of ovarian tumors, and design a novel type of ovarian cancer diagnosis system. The improved HOG feature extraction method and the gray-level concurrence matrix of LBP image are firstly adopted to extract low-level features; Then, these features are cascaded into a new feature vector, and are input into the auto-encoder neural network to learn the high-level feature. Finally, the SVM classifier is used to achieve the classification of ovarian lesion. A large number of qualitative and quantitative experiments show that the improved method has more performance than the comparisons algorithms for ovarian ultrasound lesion, and it can significantly improve the classification performance while ensuring the accuracy rate and recall rate.

scholarly journals DRAC: a delta recurrent neural network-based arithmetic coding algorithm for edge computing

2021 ◽  
Author(s):  
Bowei Shan ◽  
Yong Fang
Keyword(s):  
Neural Network ◽  
Power Consumption ◽  
Recurrent Neural Network ◽  
State Of The Art ◽  
The State ◽  
Edge Computing ◽  
Experimental Results ◽  
Arithmetic Coding ◽  
Speedup Ratio ◽  
Consumption Saving

AbstractThis paper develops an arithmetic coding algorithm based on delta recurrent neural network for edge computing devices called DRAC. Our algorithm is implemented on a Xilinx Zynq 7000 Soc board. We evaluate DRAC with four datasets and compare it with the state-of-the-art compressor DeepZip. The experimental results show that DRAC outperforms DeepZip and achieves 5X speedup ratio and 20X power consumption saving.

scholarly journals Screening of Radiological Images Suspected of Containing Lung Nodules

2022 ◽  
Vol 12 (1) ◽  
pp. 1-12
Author(s):  
Raúl Pedro Aceñero Eixarch ◽  
Raúl Díaz-Usechi Laplaza ◽  
Rafael Berlanga Llavori
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Final Diagnosis ◽  
Lung Nodules ◽  
Radiological Images ◽  
Classification Tasks ◽  
Radiological Image ◽  
Image Streams ◽  
Different Sources ◽  
And Training

This paper presents a study about screening large radiological image streams produced in hospitals for earlier detection of lung nodules. Being one of the most difficult classification tasks in the literature, our objective is to measure how well state-of-the-art classifiers can screen out the images stream to keep as many positive cases as possible in an output stream to be inspected by clinicians. We performed several experiments with different image resolutions and training datasets from different sources, always taking ResNet-152 as the base neural network. Results over existing datasets show that, contrary to other diseases like pneumonia, detecting nodules is a hard task when using only radiographies. Indeed, final diagnosis by clinicians is usually performed with much more precise images like computed tomographies.

scholarly journals An Automatic Contrast Validation Approach for Smartphone Themes

2020 ◽  
Author(s):  
Aasim Khurshid ◽  
Adriano Gil ◽  
Felipe Augusto Souza Guimarães ◽  
Mikhail Gadelha ◽  
Everlandio Fernandes
Keyword(s):  
Neural Network ◽  
Processing Time ◽  
State Of The Art ◽  
Classification Methods ◽  
Element Level ◽  
Evaluation Measures ◽  
Evaluation Approach ◽  
The Difference ◽  
Two Phases ◽  
Visual Properties

The smartphone themes submitted to the themestore are first evaluated by human experts to ensure a pleasant visual experience1. One of the main challenges in smartphone themes evaluation is to validate the contrast of the elements of the theme. Contrast refers to the difference in visual properties that makes an object distinguishable from other objects and the background. In this work, we propose an automatic themes evaluation approach that validates the contrast of Android smartphone themes among regular and non-regular at the element level. To localize the contrast affected regions, the proposed themes evaluation is divided into two phases: 1) Element extraction; and 2) Contrast evaluation. For element extraction, a customized framework is created that utilizes native Android frameworks. Following, these elements are analyzed by using a specifically designed Convolutional Neural Network (CNN) for smartphone theme elements contrast evaluation. The proposed approach is evaluated on two databases which are composed of using the real Android themes. Experiments suggest that our proposed contrast-detection network can obtain a better performance than the known state-of-the-art classification methods, in smartphone themes evaluation, based on evaluation measures like Accuracy, F1 score, processing time and others.

Sign in / Sign up

Export Citation Format

Share Document