इसे छोड़कर सामग्री पर बढ़ने के लिए

Satellite image recognition using ensemble neural networks and difference gradient positive-negative momentum

The modern machine learning theory finds application in many areas of human activity. One of the most dispersed tasks is pattern recognition on satellite images. It is difficult for a person to recognize a large number of images in a short time. It made the researchers develop the automation process...

पूर्ण विवरण

में बचाया:
ग्रंथसूची विवरण
मुख्य लेखकों: Abdulkadirov, R. I., Абдулкадиров, Р. И., Lyakhov, P. A., Ляхов, П. А., Bergerman, M. V., Бергерман, М. В., Reznikov, D. K., Резников, Д. К.
स्वरूप: Статья
भाषा:English
प्रकाशित: 2024
विषय:
ऑनलाइन पहुंच:https://dspace.ncfu.ru/handle/20.500.12258/26760
टैग : टैग जोड़ें
कोई टैग नहीं, इस रिकॉर्ड को टैग करने वाले पहले व्यक्ति बनें!
id ir-20.500.12258-26760
record_format dspace
spelling ir-20.500.12258-267602024-02-28T13:25:35Z Satellite image recognition using ensemble neural networks and difference gradient positive-negative momentum Abdulkadirov, R. I. Абдулкадиров, Р. И. Lyakhov, P. A. Ляхов, П. А. Bergerman, M. V. Бергерман, М. В. Reznikov, D. K. Резников, Д. К. Positive-negative moving averages Remote sensing Ensemble-learning Optimization methods Pattern recognition The modern machine learning theory finds application in many areas of human activity. One of the most dispersed tasks is pattern recognition on satellite images. It is difficult for a person to recognize a large number of images in a short time. It made the researchers develop the automation process, such as neural network engagement. The loss function minimization and ensemble learning raise the pattern recognition accuracy. We propose the robust difference gradient positive-negative momentum optimization algorithm that achieves the global minimum of the loss function with higher accuracy and fewer iterations than known analogs. Such an optimization algorithm contains the generalized average moving estimation approach and more effective learning rate control by additional parameters. The proposed optimizer has the regret-bound rate estimation, belonging to OT, and converges to the global minimum. However, the main problems in optimization theory are vanishing and blowing gradient values, where the standard gradient-based algorithms fail to achieve the required objective function value. The vanishing and blowing gradient problems meet in Rastrigin and Rosebrock test functions, where the proposed optimization algorithm attains the global extreme in the shortest number of iterations and has a more stable convergence process than state-of-the-art methods. Afterward, there are trained deep convolutional neural networks with different optimizers on satellite images from the University of California merced dataset containing 21 object classes, where the proposed algorithm gives the highest accuracy. There is a suggested ensemble-learning model consisting of 4 networks with different optimizers. The prediction results receive weight coefficients distributed according to the majority voting and ensemble neural network retrains with the higher pattern recognition accuracy. The suggested ensemble-learning model with the developed optimizer raised the accuracy by 1 %–4 % percentage points. 2024-02-28T13:23:59Z 2024-02-28T13:23:59Z 2024 Статья Abdulkadirov, R., Lyakhov, P., Bergerman, M., Reznikov, D. Satellite image recognition using ensemble neural networks and difference gradient positive-negative momentum // Chaos, Solitons and Fractals. - 179. - статья № 114432. - DOI: 10.1016/j.chaos.2023.114432 http://hdl.handle.net/20.500.12258/26760 en Chaos, Solitons and Fractals application/pdf application/pdf
institution СКФУ
collection Репозиторий
language English
topic Positive-negative moving averages
Remote sensing
Ensemble-learning
Optimization methods
Pattern recognition
spellingShingle Positive-negative moving averages
Remote sensing
Ensemble-learning
Optimization methods
Pattern recognition
Abdulkadirov, R. I.
Абдулкадиров, Р. И.
Lyakhov, P. A.
Ляхов, П. А.
Bergerman, M. V.
Бергерман, М. В.
Reznikov, D. K.
Резников, Д. К.
Satellite image recognition using ensemble neural networks and difference gradient positive-negative momentum
description The modern machine learning theory finds application in many areas of human activity. One of the most dispersed tasks is pattern recognition on satellite images. It is difficult for a person to recognize a large number of images in a short time. It made the researchers develop the automation process, such as neural network engagement. The loss function minimization and ensemble learning raise the pattern recognition accuracy. We propose the robust difference gradient positive-negative momentum optimization algorithm that achieves the global minimum of the loss function with higher accuracy and fewer iterations than known analogs. Such an optimization algorithm contains the generalized average moving estimation approach and more effective learning rate control by additional parameters. The proposed optimizer has the regret-bound rate estimation, belonging to OT, and converges to the global minimum. However, the main problems in optimization theory are vanishing and blowing gradient values, where the standard gradient-based algorithms fail to achieve the required objective function value. The vanishing and blowing gradient problems meet in Rastrigin and Rosebrock test functions, where the proposed optimization algorithm attains the global extreme in the shortest number of iterations and has a more stable convergence process than state-of-the-art methods. Afterward, there are trained deep convolutional neural networks with different optimizers on satellite images from the University of California merced dataset containing 21 object classes, where the proposed algorithm gives the highest accuracy. There is a suggested ensemble-learning model consisting of 4 networks with different optimizers. The prediction results receive weight coefficients distributed according to the majority voting and ensemble neural network retrains with the higher pattern recognition accuracy. The suggested ensemble-learning model with the developed optimizer raised the accuracy by 1 %–4 % percentage points.
format Статья
author Abdulkadirov, R. I.
Абдулкадиров, Р. И.
Lyakhov, P. A.
Ляхов, П. А.
Bergerman, M. V.
Бергерман, М. В.
Reznikov, D. K.
Резников, Д. К.
author_facet Abdulkadirov, R. I.
Абдулкадиров, Р. И.
Lyakhov, P. A.
Ляхов, П. А.
Bergerman, M. V.
Бергерман, М. В.
Reznikov, D. K.
Резников, Д. К.
author_sort Abdulkadirov, R. I.
title Satellite image recognition using ensemble neural networks and difference gradient positive-negative momentum
title_short Satellite image recognition using ensemble neural networks and difference gradient positive-negative momentum
title_full Satellite image recognition using ensemble neural networks and difference gradient positive-negative momentum
title_fullStr Satellite image recognition using ensemble neural networks and difference gradient positive-negative momentum
title_full_unstemmed Satellite image recognition using ensemble neural networks and difference gradient positive-negative momentum
title_sort satellite image recognition using ensemble neural networks and difference gradient positive-negative momentum
publishDate 2024
url https://dspace.ncfu.ru/handle/20.500.12258/26760
work_keys_str_mv AT abdulkadirovri satelliteimagerecognitionusingensembleneuralnetworksanddifferencegradientpositivenegativemomentum
AT abdulkadirovri satelliteimagerecognitionusingensembleneuralnetworksanddifferencegradientpositivenegativemomentum
AT lyakhovpa satelliteimagerecognitionusingensembleneuralnetworksanddifferencegradientpositivenegativemomentum
AT lâhovpa satelliteimagerecognitionusingensembleneuralnetworksanddifferencegradientpositivenegativemomentum
AT bergermanmv satelliteimagerecognitionusingensembleneuralnetworksanddifferencegradientpositivenegativemomentum
AT bergermanmv satelliteimagerecognitionusingensembleneuralnetworksanddifferencegradientpositivenegativemomentum
AT reznikovdk satelliteimagerecognitionusingensembleneuralnetworksanddifferencegradientpositivenegativemomentum
AT reznikovdk satelliteimagerecognitionusingensembleneuralnetworksanddifferencegradientpositivenegativemomentum
_version_ 1809808868734140416