Prevention and early detection of plant diseases is one of the main issues and challenges in agriculture. Farmers spend a lot of time observing and detecting diseased plants, often by looking at and analyzing plant leaves. Inadequate handling of plant disease such as late detection or the use of wrong pesticides often causes damage to crops, which causes a deterioration in the quality of food. This problem could be addressed using artificial intelligence and machine learning to detect plant diseases by processing digital images of leaves. As the leaf is the best indicator of whether the plant is healthy or not, by applying machine learning we can create predication models to detect the condition of the leaf in a shorter period of time and possibly prevent or reduce the losses. This paper describes experimenting with Detectron2 software library and Faster R-CNN neural network in order to detect the condition of the leaf. A dataset containing 6407 images was used to train the model. The original dataset has been extended by augmenting images using the RoboFlow tool. The experimentation and implementation was done using Google Colab, environment designed for cloud computing and machine learning development.
{"title":"Detection of Plant Diseases Using Leaf Images and Machine Learning","authors":"Almira Suljović, Stevan Cakic, Tomo Popović, Stevan Sandi","doi":"10.1109/INFOTEH53737.2022.9751245","DOIUrl":"https://doi.org/10.1109/INFOTEH53737.2022.9751245","url":null,"abstract":"Prevention and early detection of plant diseases is one of the main issues and challenges in agriculture. Farmers spend a lot of time observing and detecting diseased plants, often by looking at and analyzing plant leaves. Inadequate handling of plant disease such as late detection or the use of wrong pesticides often causes damage to crops, which causes a deterioration in the quality of food. This problem could be addressed using artificial intelligence and machine learning to detect plant diseases by processing digital images of leaves. As the leaf is the best indicator of whether the plant is healthy or not, by applying machine learning we can create predication models to detect the condition of the leaf in a shorter period of time and possibly prevent or reduce the losses. This paper describes experimenting with Detectron2 software library and Faster R-CNN neural network in order to detect the condition of the leaf. A dataset containing 6407 images was used to train the model. The original dataset has been extended by augmenting images using the RoboFlow tool. The experimentation and implementation was done using Google Colab, environment designed for cloud computing and machine learning development.","PeriodicalId":6839,"journal":{"name":"2022 21st International Symposium INFOTEH-JAHORINA (INFOTEH)","volume":"6 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81153031","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 : 2022-03-16DOI: 10.1109/INFOTEH53737.2022.9751321
Miro Hegedic, Petar Gregurić, Matija Golec, Mihael Gudlin
Learning Factory is one of the educational tools that can be used to learn about Industry 4.0. technologies. It is a highly complex educational environment used to simulate the real manufacturing world as closely as possible. Since there are currently many learning factories globally, this paper outlines methods used to develop a new updated learning factory directory. The directory, which was developed using cutting-edge, no-code tools, results from a review of available scientific and public sources. Directory development resulted in an updated learning factories database that facilitates research work through more user-friendly access and enables comparison and networking of learning factories.
{"title":"Development of Learning Factory Directory - DoLF","authors":"Miro Hegedic, Petar Gregurić, Matija Golec, Mihael Gudlin","doi":"10.1109/INFOTEH53737.2022.9751321","DOIUrl":"https://doi.org/10.1109/INFOTEH53737.2022.9751321","url":null,"abstract":"Learning Factory is one of the educational tools that can be used to learn about Industry 4.0. technologies. It is a highly complex educational environment used to simulate the real manufacturing world as closely as possible. Since there are currently many learning factories globally, this paper outlines methods used to develop a new updated learning factory directory. The directory, which was developed using cutting-edge, no-code tools, results from a review of available scientific and public sources. Directory development resulted in an updated learning factories database that facilitates research work through more user-friendly access and enables comparison and networking of learning factories.","PeriodicalId":6839,"journal":{"name":"2022 21st International Symposium INFOTEH-JAHORINA (INFOTEH)","volume":"31 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80356102","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 : 2022-03-16DOI: 10.1109/INFOTEH53737.2022.9751270
Dario Javor, N. Raicevic
Global adoption and use of battery electric vehicles (BEVs) is limited by their prices, driving ranges and insufficient charging infrastructure. The driving range depends on vehicle efficiency, aging, battery capacity, driving conditions, ambient temperature, etc. The effect of ambient temperature on the costs of battery electric vehicles charging in a microgrid is analyzed in this paper. The schedule of charging/discharging electric vehicles is optimized so to minimize the energy costs of the microgrid according to the day ahead energy prices given per hour. The microgrid has photovoltaic panels with estimated energy production, and it is connected to the main grid. Optimization of the microgrid electricity costs is done in program Lingo.
{"title":"The Effect of Ambient Temperature on the Costs of Battery Electric Vehicles Charging in the Microgrid","authors":"Dario Javor, N. Raicevic","doi":"10.1109/INFOTEH53737.2022.9751270","DOIUrl":"https://doi.org/10.1109/INFOTEH53737.2022.9751270","url":null,"abstract":"Global adoption and use of battery electric vehicles (BEVs) is limited by their prices, driving ranges and insufficient charging infrastructure. The driving range depends on vehicle efficiency, aging, battery capacity, driving conditions, ambient temperature, etc. The effect of ambient temperature on the costs of battery electric vehicles charging in a microgrid is analyzed in this paper. The schedule of charging/discharging electric vehicles is optimized so to minimize the energy costs of the microgrid according to the day ahead energy prices given per hour. The microgrid has photovoltaic panels with estimated energy production, and it is connected to the main grid. Optimization of the microgrid electricity costs is done in program Lingo.","PeriodicalId":6839,"journal":{"name":"2022 21st International Symposium INFOTEH-JAHORINA (INFOTEH)","volume":"8 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78902543","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 : 2022-03-16DOI: 10.1109/INFOTEH53737.2022.9751274
J. Softić, Z. Vejzovic
The study focused on assessing and testing Windows 10 to identify possible vulnerabilities and their ability to withstand cyber-attacks. CVE data, alongside other vulnerability reports, were instrumental in measuring the operating system's performance. Metasploit and Nmap were essential in penetration and intrusion experiments in a simulated environment. The study applied the following testing procedure: information gathering, scanning and results analysis, vulnerability selection, launch attacks, and gaining access to the operating system. Penetration testing involved eight attacks, two of which were effective against the different Windows 10 versions. Installing the latest version of Windows 10 did not guarantee complete protection against attacks. Further research is essential in assessing the system's vulnerabilities are recommending better solutions.
{"title":"Windows 10 Operating System: Vulnerability Assessment and Exploitation","authors":"J. Softić, Z. Vejzovic","doi":"10.1109/INFOTEH53737.2022.9751274","DOIUrl":"https://doi.org/10.1109/INFOTEH53737.2022.9751274","url":null,"abstract":"The study focused on assessing and testing Windows 10 to identify possible vulnerabilities and their ability to withstand cyber-attacks. CVE data, alongside other vulnerability reports, were instrumental in measuring the operating system's performance. Metasploit and Nmap were essential in penetration and intrusion experiments in a simulated environment. The study applied the following testing procedure: information gathering, scanning and results analysis, vulnerability selection, launch attacks, and gaining access to the operating system. Penetration testing involved eight attacks, two of which were effective against the different Windows 10 versions. Installing the latest version of Windows 10 did not guarantee complete protection against attacks. Further research is essential in assessing the system's vulnerabilities are recommending better solutions.","PeriodicalId":6839,"journal":{"name":"2022 21st International Symposium INFOTEH-JAHORINA (INFOTEH)","volume":"62 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90422994","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 : 2022-03-16DOI: 10.1109/INFOTEH53737.2022.9751325
T. Petrova, Z. Petrov
The article examines methods for separating contours from computed tomography images. The important about the contours is that they are the places where a sharp change in the brightness of adjacent pixels takes place and to highlight them must be used so called “high-pass filters”. The article examines the separation of contours by first-order differential operators. An analysis of the existing methods of contour separation in images and the results obtained from their application on tomographic images is presented.
{"title":"Visualization of Objects in Computer Tomography","authors":"T. Petrova, Z. Petrov","doi":"10.1109/INFOTEH53737.2022.9751325","DOIUrl":"https://doi.org/10.1109/INFOTEH53737.2022.9751325","url":null,"abstract":"The article examines methods for separating contours from computed tomography images. The important about the contours is that they are the places where a sharp change in the brightness of adjacent pixels takes place and to highlight them must be used so called “high-pass filters”. The article examines the separation of contours by first-order differential operators. An analysis of the existing methods of contour separation in images and the results obtained from their application on tomographic images is presented.","PeriodicalId":6839,"journal":{"name":"2022 21st International Symposium INFOTEH-JAHORINA (INFOTEH)","volume":"7 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89317235","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 : 2022-03-16DOI: 10.1109/INFOTEH53737.2022.9751339
V. Slavova, F. Andonov
This study uses a psycholinguistics approach to the task of recognizing the emotional tone of texts with the purpose of providing an additional source of information related to emotional valence (positive-negative emotion). A previous analysis found that the rates of vowel-consonant pairings (“biphones”) are strongly correlated with emotional valence. Here we apply the discovered dependencies on arbitrarily downloaded texts of Internet news items. The sub-lexical level of these texts, with a length from 0.5 to 2.5 pages, is analyzed in regard to emotional tone. The result confirms that the phonemic level composed of biphones is indicative for the emotional tone of real-life texts. The developed method relies solely on the information carried by the sounds in the language (as an independent channel of information) and can be applied in systems for classifying the emotional valence of real-world texts.
{"title":"Bad news or good news when recognizing emotional valence using phonemic content","authors":"V. Slavova, F. Andonov","doi":"10.1109/INFOTEH53737.2022.9751339","DOIUrl":"https://doi.org/10.1109/INFOTEH53737.2022.9751339","url":null,"abstract":"This study uses a psycholinguistics approach to the task of recognizing the emotional tone of texts with the purpose of providing an additional source of information related to emotional valence (positive-negative emotion). A previous analysis found that the rates of vowel-consonant pairings (“biphones”) are strongly correlated with emotional valence. Here we apply the discovered dependencies on arbitrarily downloaded texts of Internet news items. The sub-lexical level of these texts, with a length from 0.5 to 2.5 pages, is analyzed in regard to emotional tone. The result confirms that the phonemic level composed of biphones is indicative for the emotional tone of real-life texts. The developed method relies solely on the information carried by the sounds in the language (as an independent channel of information) and can be applied in systems for classifying the emotional valence of real-world texts.","PeriodicalId":6839,"journal":{"name":"2022 21st International Symposium INFOTEH-JAHORINA (INFOTEH)","volume":"108 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77488222","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 : 2022-03-16DOI: 10.1109/INFOTEH53737.2022.9751277
Borislav Đorđević, V. Timčenko, Milovan Lazić, Nikola Davidovic
The central topic of this paper is the performance comparison and potential issues of the container-based virtualization, with Docker and Podman as typical representatives. The measurements validity is managed with the use of the same testing environment, the identical hardware and software components. The testing procedure is conducted by the means of the Filebench, on CentOS Linux 7. The goal is to evaluate an impact of one and more container-based virtual machines on the file system performances. The obtained results are thoroughly explained and further presented in graphical form.
本文的中心主题是基于容器的虚拟化的性能比较和潜在问题，以Docker和Podman为典型代表。使用相同的测试环境、相同的硬件和软件组件来管理测量的有效性。测试过程是在CentOS Linux 7上通过Filebench进行的。我们的目标是评估一个或多个基于容器的虚拟机对文件系统性能的影响。对所得结果作了详尽的解释，并以图形形式进一步说明。
{"title":"Performance comparison of Docker and Podman container-based virtualization","authors":"Borislav Đorđević, V. Timčenko, Milovan Lazić, Nikola Davidovic","doi":"10.1109/INFOTEH53737.2022.9751277","DOIUrl":"https://doi.org/10.1109/INFOTEH53737.2022.9751277","url":null,"abstract":"The central topic of this paper is the performance comparison and potential issues of the container-based virtualization, with Docker and Podman as typical representatives. The measurements validity is managed with the use of the same testing environment, the identical hardware and software components. The testing procedure is conducted by the means of the Filebench, on CentOS Linux 7. The goal is to evaluate an impact of one and more container-based virtual machines on the file system performances. The obtained results are thoroughly explained and further presented in graphical form.","PeriodicalId":6839,"journal":{"name":"2022 21st International Symposium INFOTEH-JAHORINA (INFOTEH)","volume":"27 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89980729","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 : 2022-03-16DOI: 10.1109/INFOTEH53737.2022.9751259
Marko Č. Bošković, T. Šekara, M. Rapaić
In the present study, an optimization technique is performed to obtain optimal parameters of the fractional-order FOPID/PID controller for an automatic voltage regulator (AVR) system with the time delay introduced by measurement devices and communication links for data transfer. The primary aim of the controller design for AVR system is to sustain the terminal voltage of the synchronous generator (SG) within admissible ranges by adjusting exciter signals. The set of adjustable parameters of FOPID/PID controller is obtained through the maximization of the integral gain of FOPID controller under constraints on desired phase margin and two requirements on the basis of the non-symmetrical optimum principle. Resulting quality of the regulation is assessed with performance indices: settling time, overshoot and rise time, while Integral of the Absolute Error (IAE) is used as indicator of load disturbance rejection.
{"title":"An Optimal Design of 2DoF FOPID/PID Controller using Non-symmetrical Optimum Principle for an AVR System with Time Delay","authors":"Marko Č. Bošković, T. Šekara, M. Rapaić","doi":"10.1109/INFOTEH53737.2022.9751259","DOIUrl":"https://doi.org/10.1109/INFOTEH53737.2022.9751259","url":null,"abstract":"In the present study, an optimization technique is performed to obtain optimal parameters of the fractional-order FOPID/PID controller for an automatic voltage regulator (AVR) system with the time delay introduced by measurement devices and communication links for data transfer. The primary aim of the controller design for AVR system is to sustain the terminal voltage of the synchronous generator (SG) within admissible ranges by adjusting exciter signals. The set of adjustable parameters of FOPID/PID controller is obtained through the maximization of the integral gain of FOPID controller under constraints on desired phase margin and two requirements on the basis of the non-symmetrical optimum principle. Resulting quality of the regulation is assessed with performance indices: settling time, overshoot and rise time, while Integral of the Absolute Error (IAE) is used as indicator of load disturbance rejection.","PeriodicalId":6839,"journal":{"name":"2022 21st International Symposium INFOTEH-JAHORINA (INFOTEH)","volume":"1 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87261577","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 : 2022-03-16DOI: 10.1109/INFOTEH53737.2022.9751301
Radmila Jankovic Babic, Alessia Amelio, I. Draganov
Handwriting recognition is a challenging task and with the advancements in the development of the deep learning such task can be performed even for very limited documents. This paper aims to perform writer identification and retrieval from historical documents using an ensemble of convolutional neural network models that were built using the Inception-ResNet-v2 pre-trained architecture. The dataset comprises 170 images grouped in 34 classes. The results prove that the ensemble model outperforms single pre-trained models, obtaining an accuracy of 96%.
{"title":"Writer Identification From Historical Documents Using Ensemble Deep Learning Transfer Models","authors":"Radmila Jankovic Babic, Alessia Amelio, I. Draganov","doi":"10.1109/INFOTEH53737.2022.9751301","DOIUrl":"https://doi.org/10.1109/INFOTEH53737.2022.9751301","url":null,"abstract":"Handwriting recognition is a challenging task and with the advancements in the development of the deep learning such task can be performed even for very limited documents. This paper aims to perform writer identification and retrieval from historical documents using an ensemble of convolutional neural network models that were built using the Inception-ResNet-v2 pre-trained architecture. The dataset comprises 170 images grouped in 34 classes. The results prove that the ensemble model outperforms single pre-trained models, obtaining an accuracy of 96%.","PeriodicalId":6839,"journal":{"name":"2022 21st International Symposium INFOTEH-JAHORINA (INFOTEH)","volume":"134 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77375848","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 : 2022-03-16DOI: 10.1109/INFOTEH53737.2022.9751278
B. Djordjević, Z. Despotovic
This paper presents a specific application of Cuk's DC/DC converter for a wide range of input and output voltage changes, which was used as a basic converter for the realization of a digital implementation of MPPT algorithm. The control part of the converter is realized on the basis of the microcontroller PIC18F4520, company Microchip. In the paper the basic properties of the realized MPPT converter are given, as well as the key results of experimental tests obtained for different values of input power.
{"title":"Digital Implementation of MPPT Algorithm in Cuk DC/DC Power Converter Based on PIC18F4520 Microcontroller","authors":"B. Djordjević, Z. Despotovic","doi":"10.1109/INFOTEH53737.2022.9751278","DOIUrl":"https://doi.org/10.1109/INFOTEH53737.2022.9751278","url":null,"abstract":"This paper presents a specific application of Cuk's DC/DC converter for a wide range of input and output voltage changes, which was used as a basic converter for the realization of a digital implementation of MPPT algorithm. The control part of the converter is realized on the basis of the microcontroller PIC18F4520, company Microchip. In the paper the basic properties of the realized MPPT converter are given, as well as the key results of experimental tests obtained for different values of input power.","PeriodicalId":6839,"journal":{"name":"2022 21st International Symposium INFOTEH-JAHORINA (INFOTEH)","volume":"41 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85384035","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：