Pub Date : 2022-02-16DOI: 10.1109/IT54280.2022.9743529
M. Zarubica, Slobodan Dukanović, Lidija Milosavljević, Jelena N. Terzić, Vladimir Gazivoda, Luka Filipović
The paper presents an example of upgrade to the user account management system at the University of Montenegro (UoM) Information System. This upgrade involves the integration of SMS service that provides automatic sending of credentials to users via SMS messages. Usage statistics of the developed service from its launch until today is presented and recommendations for the protection of the service from unauthorized use are given. Also, description of possibilities for integration of SMS services into other UoM Information System's services is given.
{"title":"An example of SMS service development at the University of Montenegro Information System","authors":"M. Zarubica, Slobodan Dukanović, Lidija Milosavljević, Jelena N. Terzić, Vladimir Gazivoda, Luka Filipović","doi":"10.1109/IT54280.2022.9743529","DOIUrl":"https://doi.org/10.1109/IT54280.2022.9743529","url":null,"abstract":"The paper presents an example of upgrade to the user account management system at the University of Montenegro (UoM) Information System. This upgrade involves the integration of SMS service that provides automatic sending of credentials to users via SMS messages. Usage statistics of the developed service from its launch until today is presented and recommendations for the protection of the service from unauthorized use are given. Also, description of possibilities for integration of SMS services into other UoM Information System's services is given.","PeriodicalId":335678,"journal":{"name":"2022 26th International Conference on Information Technology (IT)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123240481","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 : 2022-02-16DOI: 10.1109/IT54280.2022.9743535
Turan Goktug Altundogan, Mehmet Karaköse
EEG signals are data presented by collecting electrical activities in the brain at a certain frequency. Today, applications using the EEG signal are implemented in many fields such as medicine, computer science, robotic. Visibility Graphs, on the other hand, are graphs where certain points are associated according to their visibility features in order to perform mapping and operations in areas such as robotics. Visibility Graphs are also used today to express signals. In this study, the EEG signals are expressed with visibility graphs after certain pre-processing. Then, the classification of the obtained graph depending on the clique and degree features was carried out by using deep artificial neural networks. EEG signals have a very noisy nature, and complex pre-processing and feature extractions are used in applications using EEG signals. In the proposed method, EEG signals are subjected to very simple pre-processing and classified with a 95% success rate.
{"title":"EEG Signal Classification with Deep Neural Networks using Visibility Graphs","authors":"Turan Goktug Altundogan, Mehmet Karaköse","doi":"10.1109/IT54280.2022.9743535","DOIUrl":"https://doi.org/10.1109/IT54280.2022.9743535","url":null,"abstract":"EEG signals are data presented by collecting electrical activities in the brain at a certain frequency. Today, applications using the EEG signal are implemented in many fields such as medicine, computer science, robotic. Visibility Graphs, on the other hand, are graphs where certain points are associated according to their visibility features in order to perform mapping and operations in areas such as robotics. Visibility Graphs are also used today to express signals. In this study, the EEG signals are expressed with visibility graphs after certain pre-processing. Then, the classification of the obtained graph depending on the clique and degree features was carried out by using deep artificial neural networks. EEG signals have a very noisy nature, and complex pre-processing and feature extractions are used in applications using EEG signals. In the proposed method, EEG signals are subjected to very simple pre-processing and classified with a 95% success rate.","PeriodicalId":335678,"journal":{"name":"2022 26th International Conference on Information Technology (IT)","volume":"438 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123869461","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 : 2022-02-16DOI: 10.1109/it54280.2022.9743532
{"title":"[Copyright notice]","authors":"","doi":"10.1109/it54280.2022.9743532","DOIUrl":"https://doi.org/10.1109/it54280.2022.9743532","url":null,"abstract":"","PeriodicalId":335678,"journal":{"name":"2022 26th International Conference on Information Technology (IT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121662597","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 : 2022-02-16DOI: 10.1109/IT54280.2022.9743524
Luka Martinović, Ž. Zečević, B. Krstajić
In this paper we propose a novel distributed algorithm for cooperative output regulation in networks of agents with identical dynamics. Namely, each agent utilizes local and relative output information in order to synchronize its output to the reference trajectory provided by a single node in the network. Stability analysis is carried out by the means of small-gain theorem, and it is shown that control synthesis comes down to a $mathcal{H}_{infty}$ static output feedback problem. Simulation results that verify the effectiveness of the proposed algorithm are provided.
{"title":"Regulated Output Synchronization of Multi-Agent Systems via Output Feedback","authors":"Luka Martinović, Ž. Zečević, B. Krstajić","doi":"10.1109/IT54280.2022.9743524","DOIUrl":"https://doi.org/10.1109/IT54280.2022.9743524","url":null,"abstract":"In this paper we propose a novel distributed algorithm for cooperative output regulation in networks of agents with identical dynamics. Namely, each agent utilizes local and relative output information in order to synchronize its output to the reference trajectory provided by a single node in the network. Stability analysis is carried out by the means of small-gain theorem, and it is shown that control synthesis comes down to a $mathcal{H}_{infty}$ static output feedback problem. Simulation results that verify the effectiveness of the proposed algorithm are provided.","PeriodicalId":335678,"journal":{"name":"2022 26th International Conference on Information Technology (IT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125113411","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 : 2022-02-16DOI: 10.1109/IT54280.2022.9743519
E. M. Sumner, Marcel Aach, A. Lintermann, Runar Unnthorsson, M. Riedel
Sound localization is the ability of humans to determine the source direction of sounds that they hear. Emulating this capability in virtual environments can have various societally relevant applications enabling more realistic virtual acoustics. We use a variety of artificial intelligence methods, such as machine learning via an Artificial Neural Network (ANN) model, to emulate human sound localization abilities. This paper addresses the particular challenge that the training and optimization of these models is very computationally-intensive when working with audio signal datasets. It describes the successful porting of our novel ANN model code for sound localization from limiting serial CPU-based systems to powerful, cutting-edge High-Performance Computing (HPC) resources to obtain significant speed-ups of the training and optimization process. Selected details of the code refactoring and HPC porting are described, such as adapting hyperparameter optimization algorithms to efficiently use the available HPC resources and replacing third-party libraries responsible for audio signal analysis and linear algebra. This study demonstrates that using innovative HPC systems at the Jülich Supercomputing Centre, equipped with high-tech Graphics Processing Unit (GPU) resources and based on the Modular Supercomputing Architecture, enables significant speed-ups and reduces the time-to-solution for sound localization from three days to three hours per ANN model.
{"title":"Speed-Up of Machine Learning for Sound Localization via High-Performance Computing","authors":"E. M. Sumner, Marcel Aach, A. Lintermann, Runar Unnthorsson, M. Riedel","doi":"10.1109/IT54280.2022.9743519","DOIUrl":"https://doi.org/10.1109/IT54280.2022.9743519","url":null,"abstract":"Sound localization is the ability of humans to determine the source direction of sounds that they hear. Emulating this capability in virtual environments can have various societally relevant applications enabling more realistic virtual acoustics. We use a variety of artificial intelligence methods, such as machine learning via an Artificial Neural Network (ANN) model, to emulate human sound localization abilities. This paper addresses the particular challenge that the training and optimization of these models is very computationally-intensive when working with audio signal datasets. It describes the successful porting of our novel ANN model code for sound localization from limiting serial CPU-based systems to powerful, cutting-edge High-Performance Computing (HPC) resources to obtain significant speed-ups of the training and optimization process. Selected details of the code refactoring and HPC porting are described, such as adapting hyperparameter optimization algorithms to efficiently use the available HPC resources and replacing third-party libraries responsible for audio signal analysis and linear algebra. This study demonstrates that using innovative HPC systems at the Jülich Supercomputing Centre, equipped with high-tech Graphics Processing Unit (GPU) resources and based on the Modular Supercomputing Architecture, enables significant speed-ups and reduces the time-to-solution for sound localization from three days to three hours per ANN model.","PeriodicalId":335678,"journal":{"name":"2022 26th International Conference on Information Technology (IT)","volume":"165 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125964659","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 : 2022-02-16DOI: 10.1109/IT54280.2022.9743528
Ziya Tan, M. Karakose
With the development of artificial intelligence, there are great changes especially in technology and industry sectors. The fact that deep learning and reinforcement learning studies are popular topics by researchers accelerates this change. In this article, a distributed system is presented to determine the hyper-parameters of the deep learning algorithm used for object detection at the most accurate value. One of the most important factors affecting the accuracy rate in object recognition approaches using deep learning algorithms is the determination of hyper-parameters with correct values. It may be necessary to carry out very long experiments to determine the optimum of these parameters. To solve this problem, a deep learning network used for object detection has been trained by combining the RAY distributed architecture with a deep learning algorithm. The accuracy rate is observed by changing the parameters in each iteration. For object detection, the training of the neural network we created with the CIFAR-10 dataset was carried out using CPU. In addition, thanks to the distributed architecture, each process is trained by 4 different workers. The training results and the properties of the artificial neural network are given in detail in the following sections. Accordingly, we can highlight the main contributions of this article in three points. Firstly; to show that long processes are completed in a short time, thanks to the integration of deep learning algorithms with the distributed system; training the model used to determine the optimal hyper-parameter values and the third is the presentation of the distributed deep learning approach.
{"title":"Distributed Deep Learning Approach for Optimal Hyper-Parameter Values","authors":"Ziya Tan, M. Karakose","doi":"10.1109/IT54280.2022.9743528","DOIUrl":"https://doi.org/10.1109/IT54280.2022.9743528","url":null,"abstract":"With the development of artificial intelligence, there are great changes especially in technology and industry sectors. The fact that deep learning and reinforcement learning studies are popular topics by researchers accelerates this change. In this article, a distributed system is presented to determine the hyper-parameters of the deep learning algorithm used for object detection at the most accurate value. One of the most important factors affecting the accuracy rate in object recognition approaches using deep learning algorithms is the determination of hyper-parameters with correct values. It may be necessary to carry out very long experiments to determine the optimum of these parameters. To solve this problem, a deep learning network used for object detection has been trained by combining the RAY distributed architecture with a deep learning algorithm. The accuracy rate is observed by changing the parameters in each iteration. For object detection, the training of the neural network we created with the CIFAR-10 dataset was carried out using CPU. In addition, thanks to the distributed architecture, each process is trained by 4 different workers. The training results and the properties of the artificial neural network are given in detail in the following sections. Accordingly, we can highlight the main contributions of this article in three points. Firstly; to show that long processes are completed in a short time, thanks to the integration of deep learning algorithms with the distributed system; training the model used to determine the optimal hyper-parameter values and the third is the presentation of the distributed deep learning approach.","PeriodicalId":335678,"journal":{"name":"2022 26th International Conference on Information Technology (IT)","volume":"118 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132227939","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 : 2022-02-16DOI: 10.1109/IT54280.2022.9743534
Hasan Yetiş, Mehmet Karaköse
Quantum computing is promising for image processing applications with its parallel processing capability. Today, studies are carried out to perform various image processing operations via quantum computing. In this study, a framework for window-based image processing is proposed. After encoding input images, the proposed framework keeps all the values in the relevant window in separate registers, depending on the window size. Window-based operations can be performed in parallel by applying Hadamard gate to the inputs and performing the related operations on the values in the window. The proposed framework is applied for image matching applications, which is an important branch of image processing. By comparing the searched pattern with the values in the window, it is checked whether it matches the searched pattern. Binary values are used to make the application more understandable.
{"title":"A New Framework for Quantum Image Processing and Application of Binary Template Matching","authors":"Hasan Yetiş, Mehmet Karaköse","doi":"10.1109/IT54280.2022.9743534","DOIUrl":"https://doi.org/10.1109/IT54280.2022.9743534","url":null,"abstract":"Quantum computing is promising for image processing applications with its parallel processing capability. Today, studies are carried out to perform various image processing operations via quantum computing. In this study, a framework for window-based image processing is proposed. After encoding input images, the proposed framework keeps all the values in the relevant window in separate registers, depending on the window size. Window-based operations can be performed in parallel by applying Hadamard gate to the inputs and performing the related operations on the values in the window. The proposed framework is applied for image matching applications, which is an important branch of image processing. By comparing the searched pattern with the values in the window, it is checked whether it matches the searched pattern. Binary values are used to make the application more understandable.","PeriodicalId":335678,"journal":{"name":"2022 26th International Conference on Information Technology (IT)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115472049","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 : 2022-02-16DOI: 10.1109/IT54280.2022.9743520
L. Maller, Péter Suskovics, L. Bokor
Cloud-based systems could be a solution for enabling one of the emerging technologies, Cellular-Vehicle-to-Everything (C-V2X) communication. To eliminate the limitations of centralized infrastructure elements, the Edge Cloud architecture could be the key in enhancing 5G systems' service capabilities by placing computational resources to the edge of the network, close to the users. To evaluate and validate new systems in this domain is to use model-based simulation tools. Thus, we introduce the Cloud-in-the-Loop (CiL) simulator concept. The implemented framework models the physical movement of vehicles, and based on this information, it orchestrates a complete distributed cloud system and executes various measurement scenarios. Here we focus on the distortions of a Kubernetes-based Edge Cloud environment caused by the application relocation mechanisms initiated due to user (i.e., vehicles) mobility.
{"title":"Cloud-in-the-Loop simulation of C-V2X application relocation distortions in Kubernetes based Edge Cloud environment","authors":"L. Maller, Péter Suskovics, L. Bokor","doi":"10.1109/IT54280.2022.9743520","DOIUrl":"https://doi.org/10.1109/IT54280.2022.9743520","url":null,"abstract":"Cloud-based systems could be a solution for enabling one of the emerging technologies, Cellular-Vehicle-to-Everything (C-V2X) communication. To eliminate the limitations of centralized infrastructure elements, the Edge Cloud architecture could be the key in enhancing 5G systems' service capabilities by placing computational resources to the edge of the network, close to the users. To evaluate and validate new systems in this domain is to use model-based simulation tools. Thus, we introduce the Cloud-in-the-Loop (CiL) simulator concept. The implemented framework models the physical movement of vehicles, and based on this information, it orchestrates a complete distributed cloud system and executes various measurement scenarios. Here we focus on the distortions of a Kubernetes-based Edge Cloud environment caused by the application relocation mechanisms initiated due to user (i.e., vehicles) mobility.","PeriodicalId":335678,"journal":{"name":"2022 26th International Conference on Information Technology (IT)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131047761","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 : 2022-02-16DOI: 10.1109/IT54280.2022.9743546
Ivana Cavor, Ilija Knežević, Nemanja Pudar, Lazar Mrdović, Tatijana Dlabač
In engineering education, practical classes occupies a very important role since the experimental setup and the use of advanced technology can simulate real engineering problems. This paper points out that the introduction of programmable devices in the implementation of practical classes in engineering education enables the acquisition of knowledge in a very innovative way. We also present one way to overcome the problem of realizing practical classes in conditions when students are prevented from being physically in the laboratory. The idea is to employ BBC Micro:bit (The British Broadcasting Corporation), a widely used programmable device, stemmed from its simplicity, accessibility and ability to work in groups. Its characteristics have made it highly applicable across various education levels.
{"title":"The use of micro:bit in practical classes","authors":"Ivana Cavor, Ilija Knežević, Nemanja Pudar, Lazar Mrdović, Tatijana Dlabač","doi":"10.1109/IT54280.2022.9743546","DOIUrl":"https://doi.org/10.1109/IT54280.2022.9743546","url":null,"abstract":"In engineering education, practical classes occupies a very important role since the experimental setup and the use of advanced technology can simulate real engineering problems. This paper points out that the introduction of programmable devices in the implementation of practical classes in engineering education enables the acquisition of knowledge in a very innovative way. We also present one way to overcome the problem of realizing practical classes in conditions when students are prevented from being physically in the laboratory. The idea is to employ BBC Micro:bit (The British Broadcasting Corporation), a widely used programmable device, stemmed from its simplicity, accessibility and ability to work in groups. Its characteristics have made it highly applicable across various education levels.","PeriodicalId":335678,"journal":{"name":"2022 26th International Conference on Information Technology (IT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125519241","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 : 2022-02-16DOI: 10.1109/IT54280.2022.9743538
Dejan Babic, I. Jovović, Tomo Popović, N. Kovač, Stevan Cakic
This study goes through basic principles of environmental monitoring in order to propose a simple real-time environmental monitoring based on the Internet of Things technology. The proposed solution utilizes inexpensive and widely available hardware and software components making it suitable for both personal and commercial use. The hardware of the sensor node is based on an ESP32 microcontroller equipped with sensors for environmental monitoring. The data is collected and integrated using Blynk's cloud-based web application as a backbone of the developed system. Blynk cloud platform provide features for storing, managing, and visualizing data received from monitoring device. The proposed system keeps track of air temperature, humidity, air pressure and dust-like particles concentration in the air. The system is characterized by low cost and low energy consumption. The sensor node has been installed and tested alongside a commercial system for ecological monitoring at the university building.
{"title":"An Internet of Things System for Environmental Monitoring Based on ESP32 and Blynk","authors":"Dejan Babic, I. Jovović, Tomo Popović, N. Kovač, Stevan Cakic","doi":"10.1109/IT54280.2022.9743538","DOIUrl":"https://doi.org/10.1109/IT54280.2022.9743538","url":null,"abstract":"This study goes through basic principles of environmental monitoring in order to propose a simple real-time environmental monitoring based on the Internet of Things technology. The proposed solution utilizes inexpensive and widely available hardware and software components making it suitable for both personal and commercial use. The hardware of the sensor node is based on an ESP32 microcontroller equipped with sensors for environmental monitoring. The data is collected and integrated using Blynk's cloud-based web application as a backbone of the developed system. Blynk cloud platform provide features for storing, managing, and visualizing data received from monitoring device. The proposed system keeps track of air temperature, humidity, air pressure and dust-like particles concentration in the air. The system is characterized by low cost and low energy consumption. The sensor node has been installed and tested alongside a commercial system for ecological monitoring at the university building.","PeriodicalId":335678,"journal":{"name":"2022 26th International Conference on Information Technology (IT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129045010","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：