Khoshim Rakhmanov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Khoshim Rakhmanov has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Abror Shavkatovich Buriboev
Department of Artificial Intelligence, Gachon University, Seongnam 13120, Republic of Korea
1 shared publication - Andrew Jaeyong Choi
Department of AI-Software, Gachon University, Sujeong-Gu, Seongnam-si 13120, Republic of Korea
1 shared publication E Saliev
Tashkent University of Information Technologies, 17A, Buz-2, Tashkent 100125, Uzbekistan
1 shared publication- Ergash Saliev
Research Institute for the Development of Digital Technologies and Artificial Intelligence
1 shared publication - R. Kh. Khamdamov
Tashkent University of Information Technologies, 17A, Buz-2, Tashkent 100125, Uzbekistan
1 shared publication Rustam Khamdamov
1 shared publication
Latest Publications
- Open Access
Improving Fire Detection Accuracy through Enhanced Convolutional Neural Networks and Contour Techniques
In this study, a novel method combining contour analysis with deep CNN is applied for fire detection. The method was made for fire detection using two main algorithms: one which detects the color properties of the fires, and another which analyzes the shape through contour detection. To overcome the disadvantages of previous methods, we generate a new labeled dataset, which consists of small fire instances and complex scenarios. We elaborated the dataset by selecting regions of interest (ROI) for enhanced fictional small fires and complex environment traits extracted through color characteristics and contour analysis, to better train our model regarding those more intricate features. Results of the experiment showed that our improved CNN model outperformed other networks. The accuracy, precision, recall and F1 score were 99.4%, 99.3%, 99.4% and 99.5%, respectively. The performance of our new approach is enhanced in all metrics compared to the previous CNN model with an accuracy of 99.4%. In addition, our approach beats many other state-of-the-art methods as well: Dilated CNNs (98.1% accuracy), Faster R-CNN (97.8% accuracy) and ResNet (94.3%). This result suggests that the approach can be beneficial for a variety of safety and security applications ranging from home, business to industrial and outdoor settings.
Open AccessImproving Fire Detection Accuracy through Enhanced Convolutional Neural Networks and Contour Techniques
In this study, a novel method combining contour analysis with deep CNN is applied for fire detection. The method was made for fire detection using two main algorithms: one which detects the color properties of the fires, and another which analyzes the shape through contour detection. To overcome the disadvantages of previous methods, we generate a new labeled dataset, which consists of small fire instances and complex scenarios. We elaborated the dataset by selecting regions of interest (ROI) for enhanced fictional small fires and complex environment traits extracted through color characteristics and contour analysis, to better train our model regarding those more intricate features. Results of the experiment showed that our improved CNN model outperformed other networks. The accuracy, precision, recall and F1 score were 99.4%, 99.3%, 99.4% and 99.5%, respectively. The performance of our new approach is enhanced in all metrics compared to the previous CNN model with an accuracy of 99.4%. In addition, our approach beats many other state-of-the-art methods as well: Dilated CNNs (98.1% accuracy), Faster R-CNN (97.8% accuracy) and ResNet (94.3%). This result suggests that the approach can be beneficial for a variety of safety and security applications ranging from home, business to industrial and outdoor settings.
- 3 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Advantages using of the contour analysis method for detecting fire from video images
Analysis of video data related to the rapid detection of fires plays an important role in assessing the risk of exacerbation of situations, suppression or mitigation of their consequences. However, nowadays, most fire safety systems use “point detectors” that simply sound the alarm. This article discusses the contour method as an additional test to the fire detection method based on color pixel analysis. The contour analysis method complements the color analysis method and improves the result. Algorithms and hardware software for both methods were developed, as well as a comparative analysis of the methods presented in the article in the form of tables and graphs. The method based on the analysis of object contours increases the result of fire detection and reduces the number of false alarms.
- 3 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Advantages using of the contour analysis method for detecting fire from video images
Analysis of video data related to the rapid detection of fires plays an important role in assessing the risk of exacerbation of situations, suppression or mitigation of their consequences. However, nowadays, most fire safety systems use “point detectors” that simply sound the alarm. This article discusses the contour method as an additional test to the fire detection method based on color pixel analysis. The contour analysis method complements the color analysis method and improves the result. Algorithms and hardware software for both methods were developed, as well as a comparative analysis of the methods presented in the article in the form of tables and graphs. The method based on the analysis of object contours increases the result of fire detection and reduces the number of false alarms.
- Open Access
- 1 January 2020
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1441 (1) , 012143
Classification of crops by multispectral satellite images of sentinel 2 based on the analysis of vegetation signatures
This article describes crop recognition methods from multispectral satellite imagery of Sentinel 2. The feature space includes taking into account parameters such as brightness and color of optical images over the entire channel of Sentinel 2 spectrozonal satellite imagery. The signs of multispectral images for various terrain classes in satellite images are analyzed. A comparative analysis of the classification results by the methods of “Expectation Maximization” and “k -means” has been compiled.
- 1 January 2020
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1441 (1) , 012143
Open AccessClassification of crops by multispectral satellite images of sentinel 2 based on the analysis of vegetation signatures
This article describes crop recognition methods from multispectral satellite imagery of Sentinel 2. The feature space includes taking into account parameters such as brightness and color of optical images over the entire channel of Sentinel 2 spectrozonal satellite imagery. The signs of multispectral images for various terrain classes in satellite images are analyzed. A comparative analysis of the classification results by the methods of “Expectation Maximization” and “k -means” has been compiled.
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Hardware-software complex detect smoke and fire from video images
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Hardware-software complex detect smoke and fire from video images