Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10139221
P. Burankina, V. Dementyev, A. A. Sergeev
The paper substantiates the relevance of the task of monitoring the driver's actions, formulates the requirements for the implementation of such monitoring and proposes two variants of its implementation based on the use of a high-performance platform with built-in discrete graphics card and an ordinary cell phone. The obtained quantitative performance characteristics allow us to conclude about the practical possibility of solving the problem of recognition of the driver's actions in real time, including on low-performance platforms.
{"title":"Driver action monitoring based on convolutional neural network algorithms","authors":"P. Burankina, V. Dementyev, A. A. Sergeev","doi":"10.1109/ITNT57377.2023.10139221","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139221","url":null,"abstract":"The paper substantiates the relevance of the task of monitoring the driver's actions, formulates the requirements for the implementation of such monitoring and proposes two variants of its implementation based on the use of a high-performance platform with built-in discrete graphics card and an ordinary cell phone. The obtained quantitative performance characteristics allow us to conclude about the practical possibility of solving the problem of recognition of the driver's actions in real time, including on low-performance platforms.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116505933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10138979
Vladislav Ivanov, Ivan O. Abdreev, Ekaterina Lopukhova, I. Stepanov, E. Grakhova, I. V. Kuznetsov
In energy-deficient systems, such as satellite systems for remote sensing, the issue of reducing power consumption is especially relevant. The group signal transformation has shown high efficiency in reducing the dynamic range of transmitted highly correlated signals. Such signals include, for example, signals for object positioning or multispectral analysis obtained from remote sensing devices. In the present work, the estimation of bit error rate depending on the signal-to-noise ratio and compression level of the original signals was carried out. In this research, we used the model based on the ESP32 microcontroller. We obtained the analog light sensors (photoresistors) connected to the controller to obtain highly correlated signals. The calculations of the bit error rate show that compression of the dynamic range of the transmitted signals two times, and, consequently, reduction of the transmission energy, weakly affects the error rate. However, a further increase in the compression level leads to a sharp increase.
{"title":"Evaluation of Group Signal Transformation Efficiency for Earth Remote Sensing Systems","authors":"Vladislav Ivanov, Ivan O. Abdreev, Ekaterina Lopukhova, I. Stepanov, E. Grakhova, I. V. Kuznetsov","doi":"10.1109/ITNT57377.2023.10138979","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10138979","url":null,"abstract":"In energy-deficient systems, such as satellite systems for remote sensing, the issue of reducing power consumption is especially relevant. The group signal transformation has shown high efficiency in reducing the dynamic range of transmitted highly correlated signals. Such signals include, for example, signals for object positioning or multispectral analysis obtained from remote sensing devices. In the present work, the estimation of bit error rate depending on the signal-to-noise ratio and compression level of the original signals was carried out. In this research, we used the model based on the ESP32 microcontroller. We obtained the analog light sensors (photoresistors) connected to the controller to obtain highly correlated signals. The calculations of the bit error rate show that compression of the dynamic range of the transmitted signals two times, and, consequently, reduction of the transmission energy, weakly affects the error rate. However, a further increase in the compression level leads to a sharp increase.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121998734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10139240
Vasily Rodin, A. Maksimov
In this paper, the problem of comparing portrait photographic images and forensic sketches is considered. The paper analyzes the feasibility and potential advantage of applying style transfer methods to solve this problem. A method for comparing photographic and synthetic images is proposed. It consists of the feature extraction from a pair of images, the subsequent element-by-element difference between feature vectors, and further classification. We also consider a modification of the proposed method, which uses the style transfer from a sketch to a photographic image. Experimental research of the two mentioned methods is carried out on a test set of image and sketch pairs. Its results show the advantage of the modified method over the initial one.
{"title":"Style transfer effectiveness for forensic sketch and photo matching","authors":"Vasily Rodin, A. Maksimov","doi":"10.1109/ITNT57377.2023.10139240","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139240","url":null,"abstract":"In this paper, the problem of comparing portrait photographic images and forensic sketches is considered. The paper analyzes the feasibility and potential advantage of applying style transfer methods to solve this problem. A method for comparing photographic and synthetic images is proposed. It consists of the feature extraction from a pair of images, the subsequent element-by-element difference between feature vectors, and further classification. We also consider a modification of the proposed method, which uses the style transfer from a sketch to a photographic image. Experimental research of the two mentioned methods is carried out on a test set of image and sketch pairs. Its results show the advantage of the modified method over the initial one.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126347392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10139196
A. Denisova
Source camera identification is a forensic problem used for image authentication. The identification goal is to determine the camera model by digital image. At present, the most prosperous approach to source camera identification applies neural networks to classify camera models. In my research, I provide verification and modification of the source camera identification method based on the EfficientNetB5 neural network proposed by Hadwiger and Riess. The original method is very simple in implementation and it is reported to be very efficient in camera model classification. However, I demonstrate that the original method’s performance was overestimated. Therefore, I proposed a modification of the original method using the BagNet9 network. The experimental results with Forcheim Image Dataset show that modified method gives significantly better camera identification accuracy than the original method. Thus, BagNet9 is more effective in terms of camera identification than EfficientNetB5.
{"title":"Source Camera Identification Using Neural Networks","authors":"A. Denisova","doi":"10.1109/ITNT57377.2023.10139196","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139196","url":null,"abstract":"Source camera identification is a forensic problem used for image authentication. The identification goal is to determine the camera model by digital image. At present, the most prosperous approach to source camera identification applies neural networks to classify camera models. In my research, I provide verification and modification of the source camera identification method based on the EfficientNetB5 neural network proposed by Hadwiger and Riess. The original method is very simple in implementation and it is reported to be very efficient in camera model classification. However, I demonstrate that the original method’s performance was overestimated. Therefore, I proposed a modification of the original method using the BagNet9 network. The experimental results with Forcheim Image Dataset show that modified method gives significantly better camera identification accuracy than the original method. Thus, BagNet9 is more effective in terms of camera identification than EfficientNetB5.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127428869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10139121
Alina Faskhutdinova, Daria Grigorieva, Bulat Garafutdinov, V. Mokshin
This article discusses methods for predicting stroke. It has been shown that there are different methods for solving the problem. The article presents a description of the developed model for predicting the likelihood of stroke. The system allows for a quick diagnosis of this disease based on a small number of input parameters. Several methods for implementing machine learning have been considered. The method of support vectors SVM (Support Vector Machine) was taken as a basis.
{"title":"Investigation of Machine Learning Methods for Stroke Prediction","authors":"Alina Faskhutdinova, Daria Grigorieva, Bulat Garafutdinov, V. Mokshin","doi":"10.1109/ITNT57377.2023.10139121","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139121","url":null,"abstract":"This article discusses methods for predicting stroke. It has been shown that there are different methods for solving the problem. The article presents a description of the developed model for predicting the likelihood of stroke. The system allows for a quick diagnosis of this disease based on a small number of input parameters. Several methods for implementing machine learning have been considered. The method of support vectors SVM (Support Vector Machine) was taken as a basis.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122331049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10139156
S. Safronov, M. Ivanushkin, M. Korovin, I. Kaurov, I. Tkachenko, A. Krestina
The paper considers a modern approach to the design process of the Earth remote sensing small spacecraft using information technologies. The onboard composition is considered and a block diagram of the Earth remote sensing small spacecraft is developed in order to develop an information-logical diagram of internal interaction. The developed scheme allows, already at the design stage, by setting the necessary characteristics, to quickly form the onboard composition of any spacecraft, taking into account the efficiency of the joint operation of certain devices, as well as significantly reduce the time for design work on the development of small spacecraft.
{"title":"Development of the information-logical scheme for Earth remote sensing small spacecraft","authors":"S. Safronov, M. Ivanushkin, M. Korovin, I. Kaurov, I. Tkachenko, A. Krestina","doi":"10.1109/ITNT57377.2023.10139156","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139156","url":null,"abstract":"The paper considers a modern approach to the design process of the Earth remote sensing small spacecraft using information technologies. The onboard composition is considered and a block diagram of the Earth remote sensing small spacecraft is developed in order to develop an information-logical diagram of internal interaction. The developed scheme allows, already at the design stage, by setting the necessary characteristics, to quickly form the onboard composition of any spacecraft, taking into account the efficiency of the joint operation of certain devices, as well as significantly reduce the time for design work on the development of small spacecraft.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128083999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10139159
Dmitry Averkiev, S. Demin, V. Yunusov, O. Panischev, N. Demina
In this work, based on the memory functions formalism, we carried out a cross-correlation analysis of biomedical data of complex systems of living nature. We analyzed the effects of synchronization and statistical memory effects in the mutual dynamics of neuromagnetic responses of healthy subjects in response to flickering light stimuli (red-blue, blue-green, red-green). It is shown that even with a high individuality of the studied magnetoencephalograms for each subject, it is possible to establish the nature of the interaction: the synchronization effects between certain areas of the cerebral cortex under different color combinations of light. Moreover, the revealed mutual dynamics of certain brain areas plays an important role in the functioning of the brain as an integral system, primarily under external influences. We established changes in the structure of phase portraits of orthogonal dynamic variables and spectral behavior of the analyzed biomedical signals. The results obtained are of interest for the physics of complex systems and data sciences, cognitive psychology and neurophysiology, as well as for the search for diagnostic criteria for neurological diseases, such as photosensitive epilepsy.
{"title":"The Analysis of Synchronization Effects of Human Neuromagnetic Signals in Response to Flickering Light Stimuli","authors":"Dmitry Averkiev, S. Demin, V. Yunusov, O. Panischev, N. Demina","doi":"10.1109/ITNT57377.2023.10139159","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139159","url":null,"abstract":"In this work, based on the memory functions formalism, we carried out a cross-correlation analysis of biomedical data of complex systems of living nature. We analyzed the effects of synchronization and statistical memory effects in the mutual dynamics of neuromagnetic responses of healthy subjects in response to flickering light stimuli (red-blue, blue-green, red-green). It is shown that even with a high individuality of the studied magnetoencephalograms for each subject, it is possible to establish the nature of the interaction: the synchronization effects between certain areas of the cerebral cortex under different color combinations of light. Moreover, the revealed mutual dynamics of certain brain areas plays an important role in the functioning of the brain as an integral system, primarily under external influences. We established changes in the structure of phase portraits of orthogonal dynamic variables and spectral behavior of the analyzed biomedical signals. The results obtained are of interest for the physics of complex systems and data sciences, cognitive psychology and neurophysiology, as well as for the search for diagnostic criteria for neurological diseases, such as photosensitive epilepsy.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128276751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article is devoted to digital processing of radiation signals in the field of geophysics based on spectrum analysis. With the help of these signals, it was studied whether it is possible to determine the layers of underground mineral wealth. A machine learning method was proposed to determine the layer where the ores are located. Haar’s piecewise-quadratic basis was chosen as the mathematical model of the machine learning method due to the small number of calculations. The purpose of choosing this model is that in the digital processing of signals, the number of near-zero values of spectral coefficients is large, and these values can be discarded as signal noise. This process helps us reduce the amount of data. As a result of comparing the values of spectral coefficients that are not close to zero, it gives an effective result in determining the location of the ore layer.
{"title":"Application of Machine Learning Methods for Signal Processing in Piecewise-Polynomial Bases","authors":"Hakimjon Zaynidinov, Javohir Nurmurodov, Sirojiddin Qobilov","doi":"10.1109/ITNT57377.2023.10139002","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139002","url":null,"abstract":"This article is devoted to digital processing of radiation signals in the field of geophysics based on spectrum analysis. With the help of these signals, it was studied whether it is possible to determine the layers of underground mineral wealth. A machine learning method was proposed to determine the layer where the ores are located. Haar’s piecewise-quadratic basis was chosen as the mathematical model of the machine learning method due to the small number of calculations. The purpose of choosing this model is that in the digital processing of signals, the number of near-zero values of spectral coefficients is large, and these values can be discarded as signal noise. This process helps us reduce the amount of data. As a result of comparing the values of spectral coefficients that are not close to zero, it gives an effective result in determining the location of the ore layer.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"231 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134161079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10139172
M. Karpova, M. Kirilenko
The Fresnel transform is used to simulate the propagation of paraxial optical beams in free space, and the results are usually displayed in two-dimensional form. In this paper, we consider a three-dimensional model of Hermite-Gaussian modes propagation, as well as their superposition over a given propagation interval.
{"title":"3D Modeling of Hermite-Gaussian Modes Propagation","authors":"M. Karpova, M. Kirilenko","doi":"10.1109/ITNT57377.2023.10139172","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139172","url":null,"abstract":"The Fresnel transform is used to simulate the propagation of paraxial optical beams in free space, and the results are usually displayed in two-dimensional form. In this paper, we consider a three-dimensional model of Hermite-Gaussian modes propagation, as well as their superposition over a given propagation interval.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130976953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-17DOI: 10.1109/ITNT57377.2023.10139216
Ruslan Zulkashev, M. Polyak
The article discusses application of machine learning to physiognomy. Two different neural-network models are examined as feature extractors from face images. In total three classifiers are trained and compared with each other, pursuing the goal of answering a question if it is possible to automatically verify a college degree based only on a human face. Our findings show that to a certain extent it is possible.
{"title":"Automatic analysis of face images for college degree verification","authors":"Ruslan Zulkashev, M. Polyak","doi":"10.1109/ITNT57377.2023.10139216","DOIUrl":"https://doi.org/10.1109/ITNT57377.2023.10139216","url":null,"abstract":"The article discusses application of machine learning to physiognomy. Two different neural-network models are examined as feature extractors from face images. In total three classifiers are trained and compared with each other, pursuing the goal of answering a question if it is possible to automatically verify a college degree based only on a human face. Our findings show that to a certain extent it is possible.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115017080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：