Smart city is one area with the growing use of Internet of Things and Artificial Intelligence. The concept of smart cities relies on making quality of life better, and solving important problems, such as global warming, public health, energy and resources. Smart parking management is one of the smart city use cases. This paper describes the use of deep learning algorithms to process images of parking lots and determine their current occupancy. The development of prediction models was done using PKLot dataset with 12417 images, Detectron2 software library, and Faster R-CNN algorithm. The resulting models can be integrated into parking space sensors and used for building smart parking solutions, and thus lead to more efficient use of space in urban areas, reduced traffic congestion, as well as reducing parking surfing to minimum.
{"title":"Image-Based Parking Occupancy Detection Using Deep Learning and Faster R-CNN","authors":"Zoja Šćekić, Stevan Cakic, Tomo Popović, Anja Jakovljević","doi":"10.1109/IT54280.2022.9743533","DOIUrl":"https://doi.org/10.1109/IT54280.2022.9743533","url":null,"abstract":"Smart city is one area with the growing use of Internet of Things and Artificial Intelligence. The concept of smart cities relies on making quality of life better, and solving important problems, such as global warming, public health, energy and resources. Smart parking management is one of the smart city use cases. This paper describes the use of deep learning algorithms to process images of parking lots and determine their current occupancy. The development of prediction models was done using PKLot dataset with 12417 images, Detectron2 software library, and Faster R-CNN algorithm. The resulting models can be integrated into parking space sensors and used for building smart parking solutions, and thus lead to more efficient use of space in urban areas, reduced traffic congestion, as well as reducing parking surfing to minimum.","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":"131018558","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/IT54280.2022.9743542
Serhat AtaŞ, Ismail Ilhan, Mehmet Karaköse
Artificial intelligence is used in many areas and is constantly being developed. In recent years, videos made with deep fakes, which are often heard, have also developed. The use of videos made with deep fakes as blackmail in people's lives, manipulating the videos of important people to cause anxiety on people and etc. due to the fact that it poses a threat in many areas presents a big problem today. Efforts are being made to prevent this threat by detecting deep fake videos. Deep fake detection is still not fully resolved. For this reason, prominent technology companies provide support to researchers in this field and develop deep fraud detection by suggesting methods and organizing contests on most platforms such as Kaggle. In this article, a detection method is proposed to minimize the current concern of deep forgery. In the proposed method, the Xception model with high performance and speed and the EfficientNetB4 model with high accuracy were used. The proposed method aims to achieve better results and improvements in detecting fake videos.
{"title":"An Efficient Deepfake Video Detection Approach with Combination of EfficientNet and Xception Models Using Deep Learning","authors":"Serhat AtaŞ, Ismail Ilhan, Mehmet Karaköse","doi":"10.1109/IT54280.2022.9743542","DOIUrl":"https://doi.org/10.1109/IT54280.2022.9743542","url":null,"abstract":"Artificial intelligence is used in many areas and is constantly being developed. In recent years, videos made with deep fakes, which are often heard, have also developed. The use of videos made with deep fakes as blackmail in people's lives, manipulating the videos of important people to cause anxiety on people and etc. due to the fact that it poses a threat in many areas presents a big problem today. Efforts are being made to prevent this threat by detecting deep fake videos. Deep fake detection is still not fully resolved. For this reason, prominent technology companies provide support to researchers in this field and develop deep fraud detection by suggesting methods and organizing contests on most platforms such as Kaggle. In this article, a detection method is proposed to minimize the current concern of deep forgery. In the proposed method, the Xception model with high performance and speed and the EfficientNetB4 model with high accuracy were used. The proposed method aims to achieve better results and improvements in detecting fake videos.","PeriodicalId":335678,"journal":{"name":"2022 26th International Conference on Information Technology (IT)","volume":"2 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":"125398466","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/IT54280.2022.9743530
Andrej A. Samcovic
360-degree video technology has the potential to be a useful tool in a variety of applications. This new type of video can be shot in an omni-directional format, allowing users to view the video from any angle as it is playing. Due to the development of lower-cost technologies and the massive expansion in online video content, this technology's capabilities and advantages have been shown. This paper discusses some characteristics of this technology, as well as some case studies in education, which could be useful also in pandemic scenarios.
{"title":"360-degree Video Technology with Potential Use in Educational Applications","authors":"Andrej A. Samcovic","doi":"10.1109/IT54280.2022.9743530","DOIUrl":"https://doi.org/10.1109/IT54280.2022.9743530","url":null,"abstract":"360-degree video technology has the potential to be a useful tool in a variety of applications. This new type of video can be shot in an omni-directional format, allowing users to view the video from any angle as it is playing. Due to the development of lower-cost technologies and the massive expansion in online video content, this technology's capabilities and advantages have been shown. This paper discusses some characteristics of this technology, as well as some case studies in education, which could be useful also in pandemic scenarios.","PeriodicalId":335678,"journal":{"name":"2022 26th International Conference on Information Technology (IT)","volume":"44 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":"117102568","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/IT54280.2022.9743521
M. Micev, M. Ćalasan, Milovan Radulovic
This paper demonstrates the identification of nonlinear Hammerstein-Wiener model which is applied for modelling the relation between field and terminal voltage of the synchronous generator. The field voltage of the generator stands for the input data for the nonlinear model, while the terminal voltage represents the output data. The parameters of the used nonlinear model are determined using Levenberg-Marquardt algorithm. Identification procedure is based on recording field and terminal voltage responses on reference voltage step disturbances. The proposed procedure is tested on simulation model of the 40 MVA synchronous generator from hydro power plant Perucica, realized in Matlab Simulink software, which is also experimentally verified. In order to validate the identified model, two additional tests were performed-one with the different controller parameters and other with different step disturbance on reference voltage. The presented results clearly indicate that the nonlinear Hammerstein-Wiener model accurately and precisely can determine the relation between field and terminal voltage of the generator.
{"title":"Identification of nonlinear Hammerstein-Wiener model for representing a field voltage-terminal voltage relation of synchronous generator","authors":"M. Micev, M. Ćalasan, Milovan Radulovic","doi":"10.1109/IT54280.2022.9743521","DOIUrl":"https://doi.org/10.1109/IT54280.2022.9743521","url":null,"abstract":"This paper demonstrates the identification of nonlinear Hammerstein-Wiener model which is applied for modelling the relation between field and terminal voltage of the synchronous generator. The field voltage of the generator stands for the input data for the nonlinear model, while the terminal voltage represents the output data. The parameters of the used nonlinear model are determined using Levenberg-Marquardt algorithm. Identification procedure is based on recording field and terminal voltage responses on reference voltage step disturbances. The proposed procedure is tested on simulation model of the 40 MVA synchronous generator from hydro power plant Perucica, realized in Matlab Simulink software, which is also experimentally verified. In order to validate the identified model, two additional tests were performed-one with the different controller parameters and other with different step disturbance on reference voltage. The presented results clearly indicate that the nonlinear Hammerstein-Wiener model accurately and precisely can determine the relation between field and terminal voltage of the generator.","PeriodicalId":335678,"journal":{"name":"2022 26th International Conference on Information Technology (IT)","volume":"16 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":"129503817","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/IT54280.2022.9743525
Jelena Crnogorac, Jovan Crnogorac, E. Kočan, Mališa Vučinić
To obtain insight into the network traffic of wireless sensor networks that cover large areas and operate on multiple channels, more than one sniffer needs to be deployed. In an earlier work, we proposed a distributed sniffer solution, d-Argus, which enables remote access to captured traffic. d-Argus is designed to solve the problem of duplicate packets, captured by more than one sniffer, thus providing a trace of unique network traffic. In this paper, we experimentally evaluate d-Argus by conducting experiments on OpenTestbed, a testbed at Inria Paris, with a varying number of active sensor nodes and using two sniffers. We show that the selection of the appropriate client-side buffer size largely affects the ability of d-Argus to effectively filter duplicated packets.
{"title":"Experimental evaluation of distributed sniffer solution for wireless sensor networks","authors":"Jelena Crnogorac, Jovan Crnogorac, E. Kočan, Mališa Vučinić","doi":"10.1109/IT54280.2022.9743525","DOIUrl":"https://doi.org/10.1109/IT54280.2022.9743525","url":null,"abstract":"To obtain insight into the network traffic of wireless sensor networks that cover large areas and operate on multiple channels, more than one sniffer needs to be deployed. In an earlier work, we proposed a distributed sniffer solution, d-Argus, which enables remote access to captured traffic. d-Argus is designed to solve the problem of duplicate packets, captured by more than one sniffer, thus providing a trace of unique network traffic. In this paper, we experimentally evaluate d-Argus by conducting experiments on OpenTestbed, a testbed at Inria Paris, with a varying number of active sensor nodes and using two sniffers. We show that the selection of the appropriate client-side buffer size largely affects the ability of d-Argus to effectively filter duplicated packets.","PeriodicalId":335678,"journal":{"name":"2022 26th International Conference on Information Technology (IT)","volume":"05 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":"130895909","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/IT54280.2022.9743544
Marko Kljaić, S. Scepanovic
DevOps represents an organizational approach that allows faster software development, deployment, and maintenance by uniting development (Dev) and operational (Ops) teams. The aim of this research was to find out whether and to what extent companies in Montenegro use the DevOps methodology, what are the key benefits of using this methodology in practice, and what are the biggest problems in its implementation. From a technical point of view, an attempt was made to determine the level of automated processes and the tools that are the most used in the different stages of the DevOps life cycle.
{"title":"DevOps methodology usage in IT companies in Montenegro","authors":"Marko Kljaić, S. Scepanovic","doi":"10.1109/IT54280.2022.9743544","DOIUrl":"https://doi.org/10.1109/IT54280.2022.9743544","url":null,"abstract":"DevOps represents an organizational approach that allows faster software development, deployment, and maintenance by uniting development (Dev) and operational (Ops) teams. The aim of this research was to find out whether and to what extent companies in Montenegro use the DevOps methodology, what are the key benefits of using this methodology in practice, and what are the biggest problems in its implementation. From a technical point of view, an attempt was made to determine the level of automated processes and the tools that are the most used in the different stages of the DevOps life cycle.","PeriodicalId":335678,"journal":{"name":"2022 26th International Conference on Information Technology (IT)","volume":"69 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":"122746083","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/IT54280.2022.9743539
Merve Yilmazer, M. Karakose, I. Aydin, E. Akin
Railroad track fasteners are used to connect rail components together. Control of fasteners is great importance for travel safety. Missing, broken or deformed fasteners should be detected and repaired. In this study, a new method for fault detection is proposed by using a dataset consisting of railway images recorded using an autonomous drone. In deep learning, which has the potential of self-learning from the available data, the most important factor affecting model performance is data. In this study, obtaining the rail fastener images with an autonomous drone has provided an advantage compared to the existing studies in the literature. Deep learning training was conducted with Vgg16 and ResNet101V2, which are transfer learning models, in order to determine the faults caused by the lack of fasteners. The performances of the trained models in detecting faultless and missing/faulty fasteners were compared. In the results obtained, it was seen that the training made using the ResNet101V2 model with 99% accuracy produced results with higher accuracy.
{"title":"Transfer Learning Based Fault Detection Approach for Rail Components","authors":"Merve Yilmazer, M. Karakose, I. Aydin, E. Akin","doi":"10.1109/IT54280.2022.9743539","DOIUrl":"https://doi.org/10.1109/IT54280.2022.9743539","url":null,"abstract":"Railroad track fasteners are used to connect rail components together. Control of fasteners is great importance for travel safety. Missing, broken or deformed fasteners should be detected and repaired. In this study, a new method for fault detection is proposed by using a dataset consisting of railway images recorded using an autonomous drone. In deep learning, which has the potential of self-learning from the available data, the most important factor affecting model performance is data. In this study, obtaining the rail fastener images with an autonomous drone has provided an advantage compared to the existing studies in the literature. Deep learning training was conducted with Vgg16 and ResNet101V2, which are transfer learning models, in order to determine the faults caused by the lack of fasteners. The performances of the trained models in detecting faultless and missing/faulty fasteners were compared. In the results obtained, it was seen that the training made using the ResNet101V2 model with 99% accuracy produced results with higher accuracy.","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":"132023422","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：