scholarly journals TRIGONOMETRIC SERIES IN ORTHOGONAL EXPANSIONS FOR DENSITY ESTIMATES OF DEEP IMAGE FEATURES

2018 ◽  
Vol 42 (1) ◽  
pp. 149-158 ◽  
Author(s):  
A. V. Savchenko
Keyword(s):  
Neural Network ◽  
Trigonometric Series ◽  
Probabilistic Neural Network ◽  
Principal Component ◽  
Image Features ◽  
Small Samples ◽  
Deep Convolutional Neural Networks ◽  
Orthogonal Expansions ◽  
Computational Speed ◽  
Reference Images

In this paper we study image recognition tasks in which the images are described by high dimensional feature vectors extracted with deep convolutional neural networks and principal component analysis. In particular, we focus on the problem of high computational complexity of a statistical approach with non-parametric estimates of probability density implemented by the probabilistic neural network. We propose a novel statistical classification method based on the density estimators with orthogonal expansions using trigonometric series. It is shown that this approach makes it possible to overcome the drawbacks of the probabilistic neural network caused by the memory-based approach of instance-based learning. Our experimental study with Caltech-101 and CASIA WebFace datasets demonstrates that the proposed approach reduces the error rate by 1–5 % and increases the computational speed by 1.5 – 6 times when compared to the original probabilistic neural network for small samples of reference images.

Research on air pollution system based on neural network

2020 ◽  
pp. 1-11
Author(s):  
Zhiqi Jiang ◽  
Xidong Wang
Keyword(s):  
Neural Network ◽  
Air Pollution ◽  
Image Features ◽  
Air Pollutant ◽  
Pollution Monitoring ◽  
System Model ◽  
Process Data ◽  
Deep Convolutional Neural Networks ◽  
Air Pollution Monitoring ◽  
Neural Network Algorithm

This paper conducts in-depth research and analysis on the commonly used models in the simulation process of air pollutant diffusion. Combining with the actual needs of air pollution, this paper builds an air pollution system model based on neural network based on neural network algorithm, and proposes an image classification method based on deep learning and Gaussian aggregation coding. Moreover, this paper proposes a Gaussian aggregation coding layer to encode image features extracted by deep convolutional neural networks. Learn a fixed-size dictionary to represent the features of the image for final classification. In addition, this paper constructs an air pollution monitoring system based on the actual needs of the air system. Finally, this article designs a controlled experiment to verify the model proposed in this article, uses mathematical statistics to process data, and scientifically analyze the statistical results. The research results show that the model constructed in this paper has a certain effect.

scholarly journals Research on Quality Anomaly Recognition Method Based on Optimized Probabilistic Neural Network

2020 ◽  
Vol 2020 ◽  
pp. 1-11 ◽  
Author(s):  
Li-li Li ◽  
Kun Chen ◽  
Jian-min Gao ◽  
Hui Li
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Control Chart ◽  
Control Charts ◽  
Probabilistic Neural Network ◽  
Principal Component ◽  
Original Data ◽  
Improved Genetic Algorithm ◽  
Training Time ◽  
Mixed Pattern

Aiming at the problems of the lack of abnormal instances and the lag of quality anomaly discovery in quality database, this paper proposed the method of recognizing quality anomaly from the quality control chart data by probabilistic neural network (PNN) optimized by improved genetic algorithm, which made up deficiencies of SPC control charts in practical application. Principal component analysis (PCA) reduced the dimension and extracted the feature of the original data of a control chart, which reduced the training time of PNN. PNN recognized successfully both single pattern and mixed pattern of control charts because of its simple network structure and excellent recognition effect. In order to eliminate the defect of experience value, the key parameter of PNN was optimized by the improved (SGA) single-target optimization genetic algorithm, which made PNN achieve a higher rate of recognition accuracy than PNN optimized by standard genetic algorithm. Finally, the above method was validated by a simulation experiment and proved to be the most effective method compared with traditional BP neural network, single PNN, PCA-PNN without parameters optimized, and SVM optimized by particle swarm optimization algorithm.

scholarly journals Wavelet Scattering Transform for ECG Beat Classification

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Zhishuai Liu ◽  
Guihua Yao ◽  
Qing Zhang ◽  
Junpu Zhang ◽  
Xueying Zeng
Keyword(s):  
Neural Network ◽  
Time Window ◽  
Probabilistic Neural Network ◽  
Time Windows ◽  
Principal Component ◽  
Translation Invariant ◽  
Ecg Signals ◽  
Novel Approach ◽  
Scattering Transform ◽  
Reduction Methods

An electrocardiogram (ECG) records the electrical activity of the heart; it contains rich pathological information on cardiovascular diseases, such as arrhythmia. However, it is difficult to visually analyze ECG signals due to their complexity and nonlinearity. The wavelet scattering transform can generate translation-invariant and deformation-stable representations of ECG signals through cascades of wavelet convolutions with nonlinear modulus and averaging operators. We proposed a novel approach using wavelet scattering transform to automatically classify four categories of arrhythmia ECG heartbeats, namely, nonectopic (N), supraventricular ectopic (S), ventricular ectopic (V), and fusion (F) beats. In this study, the wavelet scattering transform extracted 8 time windows from each ECG heartbeat. Two dimensionality reduction methods, principal component analysis (PCA) and time window selection, were applied on the 8 time windows. These processed features were fed to the neural network (NN), probabilistic neural network (PNN), and k-nearest neighbour (KNN) classifiers for classification. The 4th time window in combination with KNN (k=4) has achieved the optimal performance with an averaged accuracy, positive predictive value, sensitivity, and specificity of 99.3%, 99.6%, 99.5%, and 98.8%, respectively, using tenfold cross-validation. Thus, our proposed model is capable of highly accurate arrhythmia classification and will provide assistance to physicians in ECG interpretation.

scholarly journals Rapid Discrimination of Cheese Products Based on Probabilistic Neural Network and Raman Spectroscopy

2020 ◽  
Vol 2020 ◽  
pp. 1-7
Author(s):  
Zheng-Yong Zhang
Keyword(s):  
Neural Network ◽  
Raman Spectroscopy ◽  
Control Method ◽  
Probabilistic Neural Network ◽  
Principal Component ◽  
Molecular Vibration ◽  
Characteristic Peak ◽  
Statistical Process ◽  
Cheese Products ◽  
Raman Spectral Data

The aim of this work is to solve the practical problem that there are relatively few fast, intelligent, and objective methods to distinguish dairy products and to further improve the quality control methods of them. Therefore, an approach of cheese product brand discrimination method based on Raman spectroscopy and probabilistic neural network algorithm was developed. The experimental results show that the spectrum contains abundant molecular vibration information of carbohydrates, fats, proteins, and other components, and the Raman spectral data collection time of a single sample is only 100 s. Due to the high spectral similarity between samples, it is impossible to identify them with naked eyes. Characteristic peak intensity combined with statistical process control method was employed to study the fluctuation characteristics of samples. The results show that the characteristic peak of experimental samples fluctuates within a certain control limit. However, due to the high similarity between the Raman spectra of different brand samples, they cannot be effectively identified as well. This paper further studied and established the analytical approach based on Raman spectroscopy, including wavelet denoising, normalization, principal component analysis, and probabilistic neural network discrimination. In db1 wavelet processing, [−1, 1] normalization, 74 principal components (cumulative contribution rate of 100%) can realize the effective discrimination of different brands of cheese products in 1 s, with the average recognition accuracy of 96%. The discriminant method established in this work has the advantages of simple operation, rapid analysis, and accurate results. It provides a technical reference for the fight against counterfeit products and has a broad application prospect.

scholarly journals Deep Learning Using Symmetry, FAST Scores, Shape-Based Filtering and Spatial Mapping Integrated with CNN for Large Scale Image Retrieval

Symmetry ◽  
2020 ◽  
Vol 12 (4) ◽  
pp. 612
Author(s):  
Khadija Kanwal ◽  
Khawaja Tehseen Ahmad ◽  
Rashid Khan ◽  
Aliya Tabassum Abbasi ◽  
Jing Li
Keyword(s):  
Standard Deviation ◽  
Image Retrieval ◽  
Large Scale ◽  
Principal Component ◽  
Image Features ◽  
Deep Convolutional Neural Networks ◽  
Key Points ◽  
Retrieval Scheme ◽  
Large Scale Image Retrieval ◽  
Symmetric Sampling

This article presents symmetry of sampling, scoring, scaling, filtering and suppression over deep convolutional neural networks in combination with a novel content-based image retrieval scheme to retrieve highly accurate results. For this, fusion of ResNet generated signatures is performed with the innovative image features. In the first step, symmetric sampling is performed on the images from the neighborhood key points. Thereafter, the rotated sampling patterns and pairwise comparisons are performed, which return image smoothing by applying standard deviation. These values of smoothed intensity are calculated as per local gradients. Box filtering adjusts the results of approximation of Gaussian with standard deviation to the lowest scale and suppressed by non-maximal technique. The resulting feature sets are scaled at various levels with parameterized smoothened images. The principal component analysis (PCA) reduced feature vectors are combined with the ResNet generated feature. Spatial color coordinates are integrated with convolutional neural network (CNN) extracted features to comprehensively represent the color channels. The proposed method is experimentally applied on challenging datasets including Cifar-100 (10), Cifar-10 (10), ALOT (250), Corel-10000 (10), Corel-1000 (10) and Fashion (15). The presented method shows remarkable results on texture datasets ALOT with 250 categories and fashion (15). The proposed method reports significant results on Cifar-10 and Cifar-100 benchmarks. Moreover, outstanding results are obtained for the Corel-1000 dataset in comparison with state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document