scholarly journals Improving the quality of identification and filtering of micro-object images based on neural networks

2021 ◽  
Vol 304 ◽  
pp. 01007
Author(s):  
Isroil Jumanov ◽  
Olim Djumanov ◽  
Rustam Safarov
Keyword(s):  
Neural Networks ◽  
Wavelet Transforms ◽  
Dynamic Models ◽  
A Priori ◽  
Pollen Grains ◽  
Image Contour ◽  
Statistical Dynamic ◽  
Classification Of Images ◽  
Parameter Values

Constructive approaches, principles, and models for optimizing the identification of micro-objects have been developed based on the use of combined statistical, dynamic models and neural networks with mechanisms for filtering noise and foreign particles of images of medical objects and pollen grains. Algorithms for learning neural networks under conditions of a priori insufficiency, uncertainty of parameters, and low accuracy of data processing are investigated. The mechanisms of contour selection, segmentation, obtaining the boundaries of segments with hard and soft thresholds, filtering using the morphological features of the image have been developed [1]. Mechanisms for recognition and classification of images, adaptation of parameter values, tuning of the network structure, approximation and smoothing of random emissions, bursts in the image contour are proposed. A mechanism for suppressing impulse noise and noise is implemented based on various filtering methods, preserving the boundaries of objects and small-sized parts. Mathematical expressions are obtained for estimating the identification errors caused by nonstationarity, inadequacy of approximation, interpolation, and extrapolation of the image contour. A software package for the recognition and classification of micro-objects has been developed. The results were obtained for correct, incorrect recognition, as well as rejected pollen samples, which were synthesized with cubic, biquadratic, interpolation spline-functions and wavelet transforms.

scholarly journals Detection and Classification of Power Quality Disturbancewaveform Using MRA Based Modified Wavelet Transfrom and Neural Networks

2010 ◽  
Vol 61 (4) ◽  
pp. 235-240 ◽  
Author(s):  
Perumal Chandrasekar ◽  
Vijayarajan Kamaraj
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Power Quality ◽  
Wavelet Transforms ◽  
Back Propagation ◽  
Voltage Sag ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Detection and Classification of Power Quality Disturbancewaveform Using MRA Based Modified Wavelet Transfrom and Neural Networks In this paper, the modified wavelet based artificial neural network (ANN) is implemented and tested for power signal disturbances. The power signal is decomposed by using modified wavelet transform and the classification is carried by using ANN. Discrete modified wavelet transforms based signal decomposition technique is integrated with the back propagation artificial neural network model is proposed. Varieties of power quality events including voltage sag, swell, momentary interruption, harmonics, transient oscillation and voltage fluctuation are used to test the performance of the proposed approach. The simulation is carried out by using MATLAB software. The simulation results show that the proposed scheme offers superior detection and classification compared to the conventional approaches.

scholarly journals Assessing the Role of Initial Conditions in the Local Structural Identifiability of Large Dynamic Models

2021 ◽  
Author(s):  
Dominique Joubert ◽  
J.D. Stigter ◽  
Jaap Molenaar
Keyword(s):  
Systems Biology ◽  
Dynamic Models ◽  
Initial Conditions ◽  
A Priori ◽  
Model Development ◽  
Structural Identifiability ◽  
Initial Values ◽  
Zero Values ◽  
The Many ◽  
Parameter Values

Abstract Structural identifiability is a binary property that determines whether or not unique parameter values can, in principle, be estimated from error-free input-output data. The many papers that have been written on this topic collectively stress theimportance of this a priori analysis in the model development process. The story however, often ends with a structurallyunidentifiable model. This may leave a model developer with no plan of action on how to address this potential issue. We continue this model exploration journey by identifying one of the possible sources of a model’s unidentifiability: problematic initial conditions. It is well-known that certain initial values may result in the loss of local structural identifiability. Nevertheless, literature on this topic has been limited to the analysis of small toy models. Here, we present a systematic approach to detect problematic initial conditions of real-world systems biology models, that are usually not small. A model’s identifiability can often be reinstated by changing the value of such problematic initial conditions. This provides modellers an option to resolve the “unidentifiablemodel” problem. Additionally, a good understanding of which initial values should rather be avoided can be very useful during experimental design. We show how our approach works in practice by applying it to five models. First, two small benchmark models are studied toget the reader acquainted with the method. The first one shows the effect of a zero-valued problematic initial condition. The second one illustrates that the approach also yields correct results in the presence of input signals and that problematic initial conditions need not be zero-values. For the remaining three examples, we set out to identify key initial values which may result in the structural unidentifiability. The third and fourth examples involve a systems biology Epo receptor model and a JAK/STAT model, respectively. In the final Pharmacokinetics model, of which its global structural identifiability has only recently been confirmed, we indicate that there are still sets of initial values for which this property does not hold.

EPILEPTIC SPIKE DETECTION USING CONTINUOUS WAVELET TRANSFORMS AND ARTIFICIAL NEURAL NETWORKS

2010 ◽  
Vol 08 (01) ◽  
pp. 33-48 ◽  
Author(s):  
BERDAKH ABIBULLAEV ◽  
HEE DON SEO ◽  
MIN SOO KIM
Keyword(s):  
Neural Networks ◽  
Feature Extraction ◽  
Artificial Neural Networks ◽  
Wavelet Transforms ◽  
Continuous Wavelet ◽  
Continuous Wavelet Transforms ◽  
Feature Extraction Method ◽  
Artificial Neural ◽  
Epileptic Spike

We propose a new method for detection and classification of noisy recorded epileptic transients in Electroencephalograms (EEG) using the continuous wavelet transform (CWT) and artificial neural networks (ANN). The proposed method consists of a segmentation, feature extraction and classification stage. For the feature extraction stage, we use best basis mother wavelet functions and wavelet thresholding technique. For the classification stage, multilayer perceptron neural networks were implemented according to standard backpropagation learning formulations. We demonstrate the efficiency of our feature extraction method on data to improve the ANN detection performance. As a result, we achieved the accuracy in detection and classification of seizure EEG signals with 94.69%, which is relatively good comparing with the available algorithms at present time.

scholarly journals Combining Optimization Methods Using an Adaptive Meta Optimizer

Algorithms ◽  
2021 ◽  
Vol 14 (6) ◽  
pp. 186
Author(s):  
Nicola Landro ◽  
Ignazio Gallo ◽  
Riccardo La Grassa
Keyword(s):  
Neural Networks ◽  
Optimization Methods ◽  
Neural Models ◽  
Text Documents ◽  
Classification Of Images

Optimization methods are of great importance for the efficient training of neural networks. There are many articles in the literature that propose particular variants of existing optimizers. In our article, we propose the use of the combination of two very different optimizers that, when used simultaneously, can exceed the performance of the single optimizers in very different problems. We propose a new optimizer called ATMO (AdapTive Meta Optimizers), which integrates two different optimizers simultaneously weighing the contributions of both. Rather than trying to improve each single one, we leverage both at the same time, as a meta-optimizer, by taking the best of both. We have conducted several experiments on the classification of images and text documents, using various types of deep neural models, and we have demonstrated through experiments that the proposed ATMO produces better performance than the single optimizers.

scholarly journals On the (Im)Practicality of Adversarial Perturbation for Image Privacy

2021 ◽  
Vol 2021 (1) ◽  
pp. 85-106
Author(s):  
Arezoo Rajabi ◽  
Rakesh B. Bobba ◽  
Mike Rosulek ◽  
Charles V. Wright ◽  
Wu-chi Feng
Keyword(s):  
Neural Networks ◽  
Face Recognition ◽  
Convolutional Neural Networks ◽  
Family Members ◽  
High Accuracy ◽  
Automated Recognition ◽  
Privacy Concerns ◽  
Classification Of Images

AbstractImage hosting platforms are a popular way to store and share images with family members and friends. However, such platforms typically have full access to images raising privacy concerns. These concerns are further exacerbated with the advent of Convolutional Neural Networks (CNNs) that can be trained on available images to automatically detect and recognize faces with high accuracy.Recently, adversarial perturbations have been proposed as a potential defense against automated recognition and classification of images by CNNs. In this paper, we explore the practicality of adversarial perturbation-based approaches as a privacy defense against automated face recognition. Specifically, we first identify practical requirements for such approaches and then propose two practical adversarial perturbation approaches – (i) learned universal ensemble perturbations (UEP), and (ii) k-randomized transparent image overlays (k-RTIO) that are semantic adversarial perturbations. We demonstrate how users can generate effective transferable perturbations under realistic assumptions with less effort.We evaluate the proposed methods against state-of-theart online and offline face recognition models, Clarifai.com and DeepFace, respectively. Our findings show that UEP and k-RTIO respectively achieve more than 85% and 90% success against face recognition models. Additionally, we explore potential countermeasures that classifiers can use to thwart the proposed defenses. Particularly, we demonstrate one effective countermeasure against UEP.

Sign in / Sign up

Export Citation Format

Share Document