Generative Adversarial Neural Network for Creating Photorealistic Images

Striuk, Oleksandr; Kondratenko, Yuriy; Sidenko, Ievgen; Vorobyova, Alla

doi:10.1109/atit50783.2020.9349326

Cited by 10 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We performed the training in a webbased Kaggle environment using a GPU as the main processing unit. The models were trained for a fixed number of epochs [6,7].…”

Section: Optimization Strategy In Gan Design: Experimental Resultsmentioning

confidence: 99%

“…We trained the generator and discriminator alternately, with the discriminator trained first and then the generator [6,7].…”

Section: Optimization Strategy In Gan Design: Experimental Resultsmentioning

confidence: 99%

“…The primary motivation behind GANs is to create high-quality synthetic data for various applications, such as image, photo, and video generation [2,3]. Further advancements in GANs development eventually demonstrated huge progress in such significant scientific and applied domains as anomaly detection [4], cybersecurity [5], medicine and drug discovery, forensics, material science, and astronomy research [3,6,7].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimization Strategy for Generative Adversarial Networks Design

Striuk,

Kondratenko

2023

IJC

View full text Add to dashboard Cite

Generative Adversarial Networks (GANs) are a powerful class of deep learning models that can generate realistic synthetic data. However, designing and optimizing GANs can be a difficult task due to various technical challenges. The article provides a comprehensive analysis of solution methods for GAN performance optimization. The research covers a range of GAN design components, including loss functions, activation functions, batch normalization, weight clipping, gradient penalty, stability problems, performance evaluation, mini-batch discrimination, and other aspects. The article reviews various techniques used to address these challenges and highlights the advancements in the field. The article offers an up-to-date overview of the state-of-the-art methods for structuring, designing, and optimizing GANs, which will be valuable for researchers and practitioners. The implementation of the optimization strategy for the design of standard and deep convolutional GANs (handwritten digits and fingerprints) developed by the authors is discussed in detail, the obtained results confirm the effectiveness of the proposed optimization approach.

show abstract

“…We performed the training in a webbased Kaggle environment using a GPU as the main processing unit. The models were trained for a fixed number of epochs [6,7].…”

Section: Optimization Strategy In Gan Design: Experimental Resultsmentioning

confidence: 99%

“…We trained the generator and discriminator alternately, with the discriminator trained first and then the generator [6,7].…”

Section: Optimization Strategy In Gan Design: Experimental Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimization Strategy for Generative Adversarial Networks Design

Striuk,

Kondratenko

2023

IJC

View full text Add to dashboard Cite

show abstract

“…The goal of NN training is to minimize the false negative decision that degrades recognition accuracy [26,[30][31][32]. The "Precision", "Recall" and "F1-score" values are calculated according to the following formulas:…”

Section: Technologies For Object Recognition In Imagesmentioning

confidence: 99%

Mobile Recognition of Image Components Based on Machine Learning Methods

Kondratenko,

Sidenko,

Saliutin

et al. 2024

JMM

View full text Add to dashboard Cite

This paper is related to the recognition of certain components in images using machine learning methods and mobile technologies. The main result of this work is a developed system for recognizing the presence of a mask on the face using an image, which provides all the necessary information in real-time about the presence or absence of a mask on the face. When the program is turned off, statistics about the presence/absence of the mask will be recorded in the database. To achieve the goal, the following tasks were solved: the current state of the task of recognizing the presence of a mask on a person’s face was analysed; existing analogs of the systems were analysed; the necessary neural network architecture was selected as one of the machine learning methods; developed a system for recognizing the presence of a mask on the face using the necessary libraries; a user graphical interface, a database model for recording statistics and additional functionality have been developed; conduct testing. Practical application has a fairly wide range, in particular, the developed intelligent system is intended for use in the subway, industrial enterprises, state institutions, educational institutions, offices, and other public places. The developed system recognizes and records statistics about the presence of a mask on a person’s face using neural networks.

show abstract

“…In recent years, the role of machine learning has significantly increased. Machine learning techniques have many successful applications in different areas of human activity, in particular, in medicine [ 4 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 ], agriculture [ 32 , 33 , 34 , 35 , 36 ], transportation [ 37 , 38 , 39 , 40 , 41 , 42 ], energy production [ 43 , 44 ], finance markets [ 45 ], investment policy [ 46 ] and research [ 47 ]. Statistical learning theory is efficiently used for processing data from sensors in real-time based on effective multi-output Gaussian processes [ 48 ] and for prognosis of the state of technical objects using canonical decomposition of a random sequence [ 49 ].…”

Section: Related Work and Problem Statementmentioning

confidence: 99%

Machine Learning Techniques for Increasing Efficiency of the Robot’s Sensor and Control Information Processing

Kondratenko

Atamanyuk

Sidenko

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Real-time systems are widely used in industry, including technological process control systems, industrial automation systems, SCADA systems, testing, and measuring equipment, and robotics. The efficiency of executing an intelligent robot’s mission in many cases depends on the properties of the robot’s sensor and control systems in providing the trajectory planning, recognition of the manipulated objects, adaptation of the desired clamping force of the gripper, obstacle avoidance, and so on. This paper provides an analysis of the approaches and methods for real-time sensor and control information processing with the application of machine learning, as well as successful cases of machine learning application in the synthesis of a robot’s sensor and control systems. Among the robotic systems under investigation are (a) adaptive robots with slip displacement sensors and fuzzy logic implementation for sensor data processing, (b) magnetically controlled mobile robots for moving on inclined and ceiling surfaces with neuro-fuzzy observers and neuro controllers, and (c) robots that are functioning in unknown environments with the prediction of the control system state using statistical learning theory. All obtained results concern the main elements of the two-component robotic system with the mobile robot and adaptive manipulation robot on a fixed base for executing complex missions in non-stationary or uncertain conditions. The design and software implementation stage involves the creation of a structural diagram and description of the selected technologies, training a neural network for recognition and classification of geometric objects, and software implementation of control system components. The Swift programming language is used for the control system design and the CreateML framework is used for creating a neural network. Among the main results are: (a) expanding the capabilities of the intelligent control system by increasing the number of classes for recognition from three (cube, cylinder, and sphere) to five (cube, cylinder, sphere, pyramid, and cone); (b) increasing the validation accuracy (to 100%) for recognition of five different classes using CreateML (YOLOv2 architecture); (c) increasing the training accuracy (to 98.02%) and testing accuracy (to 98.0%) for recognition of five different classes using Torch library (ResNet34 architecture) in less time and number of epochs compared with Create ML (YOLOv2 architecture); (d) increasing the training accuracy (to 99.75%) and testing accuracy (to 99.2%) for recognition of five different classes using Torch library (ResNet34 architecture) and fine-tuning technology; and (e) analyzing the effect of dataset size impact on recognition accuracy with ResNet34 architecture and fine-tuning technology. The results can help to choose efficient (a) design approaches for control robotic devices, (b) machine-learning methods for performing pattern recognition and classification, and (c) computer technologies for designing control systems and simulating robotic devices.

show abstract

Generative Adversarial Neural Network for Creating Photorealistic Images

Cited by 10 publications

References 15 publications

Optimization Strategy for Generative Adversarial Networks Design

Optimization Strategy for Generative Adversarial Networks Design

Mobile Recognition of Image Components Based on Machine Learning Methods

Machine Learning Techniques for Increasing Efficiency of the Robot’s Sensor and Control Information Processing

Contact Info

Product

Resources

About