Pub Date : 2019-09-01DOI: 10.1109/IDAACS.2019.8924248
L. Czúni, K. Alaya
The detection/recognition of trees (trunks and branches) from 2D images is a challenging task in image processing. The large variety of visual appearance, environmental conditions, and occlusion make it an ill-posed problem. In our work we overview different approaches to solve this problem including the performance analysis of a pixel-level clustering and a neural network based approach. Besides discussing low-level approaches we proceed from low-level (pixel-level) representations to a high-level model using graphs. Thus the problem is transformed to fitting graph structures (vertices and edges) to 2D images based on appearance, and on prior information about trees. We use Reversible Jump Markov Chain Monte Carlo optimization to solve the energy optimization problem corresponding to the maximization of the probability of the graph model created in a Marked Point Process. Besides the color information (which can be modeled by Gaussian mixtures or convolutional neural networks) other properties (such as width, connections, overlapping of vertices, and direction of branches) can be coded by different energy terms corresponding to probability. Our new approach has the advantage that it does not require significant training and can result in a high-level graph representation. We present our initial results in this article thus the recognition of overlapping branches and occlusion by other trees is not presented in this paper.
{"title":"Low- and High-level Methods for Tree Segmentation","authors":"L. Czúni, K. Alaya","doi":"10.1109/IDAACS.2019.8924248","DOIUrl":"https://doi.org/10.1109/IDAACS.2019.8924248","url":null,"abstract":"The detection/recognition of trees (trunks and branches) from 2D images is a challenging task in image processing. The large variety of visual appearance, environmental conditions, and occlusion make it an ill-posed problem. In our work we overview different approaches to solve this problem including the performance analysis of a pixel-level clustering and a neural network based approach. Besides discussing low-level approaches we proceed from low-level (pixel-level) representations to a high-level model using graphs. Thus the problem is transformed to fitting graph structures (vertices and edges) to 2D images based on appearance, and on prior information about trees. We use Reversible Jump Markov Chain Monte Carlo optimization to solve the energy optimization problem corresponding to the maximization of the probability of the graph model created in a Marked Point Process. Besides the color information (which can be modeled by Gaussian mixtures or convolutional neural networks) other properties (such as width, connections, overlapping of vertices, and direction of branches) can be coded by different energy terms corresponding to probability. Our new approach has the advantage that it does not require significant training and can result in a high-level graph representation. We present our initial results in this article thus the recognition of overlapping branches and occlusion by other trees is not presented in this paper.","PeriodicalId":415006,"journal":{"name":"2019 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS)","volume":"216 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121879219","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 : 2019-09-01DOI: 10.1109/IDAACS.2019.8924233
A. Lagunov, A. Losunov
The Arctic is a very promising region for hydrocarbon production. At the same time, this region is very severe in terms of climate. Low temperatures and high humidity complicate metals welding in the Arctic. These conditions require the protection of the welding zone for high-quality welding. The authors propose to use gas-shielded welding. The authors studied the effect of conditions of gas flow from the nozzle on the characteristics of the jet when gas welding in the Arctic. It was found that the gas flow from the nozzle is effected by the shape and aerodynamic quality of the nozzle flow passage; the type and thickness of the boundary layer on the inner side of the nozzle; the degree of flow turbulence at the nozzle outlet; variation of the velocity at the nozzle outlet; the ratio of the density of the gas jet and surrounding air.
{"title":"Simulation of Gas Flow for Welding Process Control in the Arctic Environment","authors":"A. Lagunov, A. Losunov","doi":"10.1109/IDAACS.2019.8924233","DOIUrl":"https://doi.org/10.1109/IDAACS.2019.8924233","url":null,"abstract":"The Arctic is a very promising region for hydrocarbon production. At the same time, this region is very severe in terms of climate. Low temperatures and high humidity complicate metals welding in the Arctic. These conditions require the protection of the welding zone for high-quality welding. The authors propose to use gas-shielded welding. The authors studied the effect of conditions of gas flow from the nozzle on the characteristics of the jet when gas welding in the Arctic. It was found that the gas flow from the nozzle is effected by the shape and aerodynamic quality of the nozzle flow passage; the type and thickness of the boundary layer on the inner side of the nozzle; the degree of flow turbulence at the nozzle outlet; variation of the velocity at the nozzle outlet; the ratio of the density of the gas jet and surrounding air.","PeriodicalId":415006,"journal":{"name":"2019 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122606389","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 : 2019-09-01DOI: 10.1109/IDAACS.2019.8924413
Wenshuo Bian, Chunzhi Wang, Z. Ye, Lingyu Yan
In order to improve the accuracy and generalization performance of text sentiment analysis model, an integrated learning model is proposed in this paper, which includes three different classification algorithms - Logistic regression, support vector machine and K-Neighborhood algorithm. Compared with single classification algorithm, this algorithm shows better accuracy. The experimental results show that the model has good generalization performance and robustness.
{"title":"Emotional Text Analysis Based on Ensemble Learning of Three Different Classification Algorithms","authors":"Wenshuo Bian, Chunzhi Wang, Z. Ye, Lingyu Yan","doi":"10.1109/IDAACS.2019.8924413","DOIUrl":"https://doi.org/10.1109/IDAACS.2019.8924413","url":null,"abstract":"In order to improve the accuracy and generalization performance of text sentiment analysis model, an integrated learning model is proposed in this paper, which includes three different classification algorithms - Logistic regression, support vector machine and K-Neighborhood algorithm. Compared with single classification algorithm, this algorithm shows better accuracy. The experimental results show that the model has good generalization performance and robustness.","PeriodicalId":415006,"journal":{"name":"2019 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123819321","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 : 2019-09-01DOI: 10.1109/IDAACS.2019.8924423
V. Kochan, Oleksandr Matsiuk, N. Kunanets, V. Pasichnyk, Oleksiy Roshchupkin, A. Sachenko, I. Turchenko, O. Duda, V. Semaniuk, Svitlana Romaniv
The Internet of Things (IoT) includes a large set of sensors of various physical quantities, operating principles and parameters. In this case, sensor errors are traditionally dominant in measuring channels. In this paper general methods of increasing the accuracy of sensors using neural networks are considered. Due to the generalization of properties, neural networks can significantly improve the accuracy of sensors with reduced complexity of the transition to their individual transformation functions.
{"title":"Sensing in IoT for Smart City Systems","authors":"V. Kochan, Oleksandr Matsiuk, N. Kunanets, V. Pasichnyk, Oleksiy Roshchupkin, A. Sachenko, I. Turchenko, O. Duda, V. Semaniuk, Svitlana Romaniv","doi":"10.1109/IDAACS.2019.8924423","DOIUrl":"https://doi.org/10.1109/IDAACS.2019.8924423","url":null,"abstract":"The Internet of Things (IoT) includes a large set of sensors of various physical quantities, operating principles and parameters. In this case, sensor errors are traditionally dominant in measuring channels. In this paper general methods of increasing the accuracy of sensors using neural networks are considered. Due to the generalization of properties, neural networks can significantly improve the accuracy of sensors with reduced complexity of the transition to their individual transformation functions.","PeriodicalId":415006,"journal":{"name":"2019 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS)","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125210847","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 : 2019-09-01DOI: 10.1109/IDAACS.2019.8924425
G. Shilo, V. Beskorovainyi, E. Ogrenich, Nataliia Furmanova, N. Myronova
Thermal mode of electronic devices with forced air cooling system is researched. The influence of air velocity on the thermal mode of electronic modules is investigated. The algorithms of optimizing the mass and thermal resistance of electronic devices are proposed. These algorithms can be applied for finned channel and heatsink covers. Thermal parameters of electronic devices are obtained using advanced computer-aided design systems.
{"title":"Thermal Design of Electronic Devices with a Forced Cooling System","authors":"G. Shilo, V. Beskorovainyi, E. Ogrenich, Nataliia Furmanova, N. Myronova","doi":"10.1109/IDAACS.2019.8924425","DOIUrl":"https://doi.org/10.1109/IDAACS.2019.8924425","url":null,"abstract":"Thermal mode of electronic devices with forced air cooling system is researched. The influence of air velocity on the thermal mode of electronic modules is investigated. The algorithms of optimizing the mass and thermal resistance of electronic devices are proposed. These algorithms can be applied for finned channel and heatsink covers. Thermal parameters of electronic devices are obtained using advanced computer-aided design systems.","PeriodicalId":415006,"journal":{"name":"2019 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129801301","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 : 2019-09-01DOI: 10.1109/IDAACS.2019.8924391
Andrii Cheredarchuk, Oleksii Kashpirovskyi, G. Kriukova, Maksym Sarana
In the last few years image processing and analysis, particularly, video and image compression became very important due to immense development of new multi-media products, surveillance systems, automotive industry, etc, and the shortage of bandwidth and storage space of the memory. In the paper we consider a mathematical model as an approach to image processing, compression and restoration. We use edge detection algorithm to construct infinite system of difference equations, which is encoded by means of given family of functions, i.e. low degree polynomials, piece-wise linear functions or Heaviside step functions. Corresponding encoding and decoding algorithm is proposed, along with comprehensive theoretical background. The existence and uniqueness of decoded image is considered. This paper presents some preliminary study of the advantages and drawbacks of the approach and indicates areas of possible further research.
{"title":"Towards Image Processing Based on System of Difference Equations","authors":"Andrii Cheredarchuk, Oleksii Kashpirovskyi, G. Kriukova, Maksym Sarana","doi":"10.1109/IDAACS.2019.8924391","DOIUrl":"https://doi.org/10.1109/IDAACS.2019.8924391","url":null,"abstract":"In the last few years image processing and analysis, particularly, video and image compression became very important due to immense development of new multi-media products, surveillance systems, automotive industry, etc, and the shortage of bandwidth and storage space of the memory. In the paper we consider a mathematical model as an approach to image processing, compression and restoration. We use edge detection algorithm to construct infinite system of difference equations, which is encoded by means of given family of functions, i.e. low degree polynomials, piece-wise linear functions or Heaviside step functions. Corresponding encoding and decoding algorithm is proposed, along with comprehensive theoretical background. The existence and uniqueness of decoded image is considered. This paper presents some preliminary study of the advantages and drawbacks of the approach and indicates areas of possible further research.","PeriodicalId":415006,"journal":{"name":"2019 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129705478","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 : 2019-09-01DOI: 10.1109/IDAACS.2019.8924303
Yannick Fanchette, H. Ramenah, Philippe Casin, M. Benne, C. Tanougast, K. Adjallah
The high irradiance in tropical area is certainly favorable to photovoltaic (PV) power output, since the efficiency depends on the solar radiation intensity. However the increase of cells temperature causes conversely a fall of the yield of the modules. This decrease in the performance of PV modules due to temperature effect also causes proportional voltage decrease. This drop in performance is at the expense of destabilisation of the electrical network and if the electrical power output of modules is planned for a total grid injection. A time series may be useful in forecasting another time series and this statistical hypothesis test is called the Granger causality test. In this paper, we show that the Granger causality can be applied to PV parameters time series and an error correction model is used to determine a long term relationship of power output for PV systems.
{"title":"Predictive Causality of Granger Test for Long Run Equilibrium to Photovoltaic System","authors":"Yannick Fanchette, H. Ramenah, Philippe Casin, M. Benne, C. Tanougast, K. Adjallah","doi":"10.1109/IDAACS.2019.8924303","DOIUrl":"https://doi.org/10.1109/IDAACS.2019.8924303","url":null,"abstract":"The high irradiance in tropical area is certainly favorable to photovoltaic (PV) power output, since the efficiency depends on the solar radiation intensity. However the increase of cells temperature causes conversely a fall of the yield of the modules. This decrease in the performance of PV modules due to temperature effect also causes proportional voltage decrease. This drop in performance is at the expense of destabilisation of the electrical network and if the electrical power output of modules is planned for a total grid injection. A time series may be useful in forecasting another time series and this statistical hypothesis test is called the Granger causality test. In this paper, we show that the Granger causality can be applied to PV parameters time series and an error correction model is used to determine a long term relationship of power output for PV systems.","PeriodicalId":415006,"journal":{"name":"2019 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129637716","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 : 2019-09-01DOI: 10.1109/IDAACS.2019.8924428
O. Savenko, A. Sachenko, S. Lysenko, G. Markowsky
This article presents the technique for botnet detection using the distributed systems in the local area network. Distributed system contains host and network levels. At the host level, the botnets detection is based on Bayes classification. In order to perform the classification, the classes and subclasses were constructed on the basis of botnets patterns. An algorithm for classifier training was developed. The network level provides the exchange of the classification results for the knowledge transfer to the rest of the antivirus program units of the distributed system.
{"title":"Botnet Detection Approach for the Distributed Systems","authors":"O. Savenko, A. Sachenko, S. Lysenko, G. Markowsky","doi":"10.1109/IDAACS.2019.8924428","DOIUrl":"https://doi.org/10.1109/IDAACS.2019.8924428","url":null,"abstract":"This article presents the technique for botnet detection using the distributed systems in the local area network. Distributed system contains host and network levels. At the host level, the botnets detection is based on Bayes classification. In order to perform the classification, the classes and subclasses were constructed on the basis of botnets patterns. An algorithm for classifier training was developed. The network level provides the exchange of the classification results for the knowledge transfer to the rest of the antivirus program units of the distributed system.","PeriodicalId":415006,"journal":{"name":"2019 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128679365","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 : 2019-09-01DOI: 10.1109/IDAACS.2019.8924390
Y. Monakhov, M. Monakhov, Sergei D. Luchinkin, A.P. Kuznetsova, Maria M. Monakhova
This article discusses existing approaches to building regional scale networks. Authors offer a mathematical model of network growth process, on the basis of which simulation is performed. The availability characteristic is used as criterion for measuring optimality. This report describes the mechanism for measuring network availability and contains propositions to make changes to the procedure for designing of regional networks, which can improve its qualitative characteristics. The efficiency of changes is confirmed by simulation.
{"title":"Availability as a Metric for Region-Scale Telecommunication Designs","authors":"Y. Monakhov, M. Monakhov, Sergei D. Luchinkin, A.P. Kuznetsova, Maria M. Monakhova","doi":"10.1109/IDAACS.2019.8924390","DOIUrl":"https://doi.org/10.1109/IDAACS.2019.8924390","url":null,"abstract":"This article discusses existing approaches to building regional scale networks. Authors offer a mathematical model of network growth process, on the basis of which simulation is performed. The availability characteristic is used as criterion for measuring optimality. This report describes the mechanism for measuring network availability and contains propositions to make changes to the procedure for designing of regional networks, which can improve its qualitative characteristics. The efficiency of changes is confirmed by simulation.","PeriodicalId":415006,"journal":{"name":"2019 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS)","volume":"154 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127281017","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 : 2019-09-01DOI: 10.1109/IDAACS.2019.8924355
F. Alilat, R. Yahiaoui
An efficient coding leading to the implementation on FPGA of an optimal architecture of a multilayer Perceptron is proposed. The implementation of this architecture meets the requirements of embark, on the one hand by minimizing the consumed power, the execution time, the logical resources used, etc ‥) and on the other hand by ensuring the portability of the computer application (the ability of the latter to run on different platforms and environments). Massive parallelization, efficient coding of the sigmoid and pipeline processing are used. The neuronal approach developed and implemented on FPGA was evaluated in the context of the application on objective criteria according to the two aspects of software and hardware. The results obtained are in line with expectations and objectives.
{"title":"MLP on FPGA: Optimal Coding of Data and Activation Function","authors":"F. Alilat, R. Yahiaoui","doi":"10.1109/IDAACS.2019.8924355","DOIUrl":"https://doi.org/10.1109/IDAACS.2019.8924355","url":null,"abstract":"An efficient coding leading to the implementation on FPGA of an optimal architecture of a multilayer Perceptron is proposed. The implementation of this architecture meets the requirements of embark, on the one hand by minimizing the consumed power, the execution time, the logical resources used, etc ‥) and on the other hand by ensuring the portability of the computer application (the ability of the latter to run on different platforms and environments). Massive parallelization, efficient coding of the sigmoid and pipeline processing are used. The neuronal approach developed and implemented on FPGA was evaluated in the context of the application on objective criteria according to the two aspects of software and hardware. The results obtained are in line with expectations and objectives.","PeriodicalId":415006,"journal":{"name":"2019 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116453641","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：