Pub Date : 2018-09-01DOI: 10.1109/SISY.2018.8524757
P. Krammer, M. Kvassay, L. Hluchý
This paper deals with regression tasks on real-valued numerical data attributes. A special data transformation formulated in our earlier work is combined with a new and enhanced weighting strategy in order to improve prediction accuracy. The proposed data modelling approach offers several advantages: it does not depend on the particular regression model used and it enables the analyst to calculate tolerance interval estimates as well as the probability that the target attribute exceeds arbitrary predefined thresholds. We tested our approach on three real-world datasets. In all the three cases it reliably improved and stabilized the prediction accuracy (measured by the average root mean squared error for each dataset) as well as the quality of tolerance interval estimates.
{"title":"Enhanced Data Modelling Approach with Interval Estimation","authors":"P. Krammer, M. Kvassay, L. Hluchý","doi":"10.1109/SISY.2018.8524757","DOIUrl":"https://doi.org/10.1109/SISY.2018.8524757","url":null,"abstract":"This paper deals with regression tasks on real-valued numerical data attributes. A special data transformation formulated in our earlier work is combined with a new and enhanced weighting strategy in order to improve prediction accuracy. The proposed data modelling approach offers several advantages: it does not depend on the particular regression model used and it enables the analyst to calculate tolerance interval estimates as well as the probability that the target attribute exceeds arbitrary predefined thresholds. We tested our approach on three real-world datasets. In all the three cases it reliably improved and stabilized the prediction accuracy (measured by the average root mean squared error for each dataset) as well as the quality of tolerance interval estimates.","PeriodicalId":6647,"journal":{"name":"2018 IEEE 16th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"52 1","pages":"000179-000184"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74240890","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 : 2018-09-01DOI: 10.1109/SISY.2018.8524826
L. Trajković
In this motivational talk, I will talk about the role that education plays in our lives and careers. I will revisit various life and career choices, compare experiences in industrial and academic jobs, and talk about opportunities when volunteering for professional organizations. In closure, I will emphasis the importance and power of commitment to always try to achieve one's best.
{"title":"You and Your Career","authors":"L. Trajković","doi":"10.1109/SISY.2018.8524826","DOIUrl":"https://doi.org/10.1109/SISY.2018.8524826","url":null,"abstract":"In this motivational talk, I will talk about the role that education plays in our lives and careers. I will revisit various life and career choices, compare experiences in industrial and academic jobs, and talk about opportunities when volunteering for professional organizations. In closure, I will emphasis the importance and power of commitment to always try to achieve one's best.","PeriodicalId":6647,"journal":{"name":"2018 IEEE 16th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"40 1","pages":"000013-000014"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77585361","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 : 2018-09-01DOI: 10.1109/SISY.2018.8524616
Máté Tóth, D. Stojcsics, Zsolt Domozi, I. Lovas
Nowadays the autonomous robots are spreading more widely, meanwhile the people can meet such devices in everyday life, which can do different tasks independently. The robots are equipped with sensors to sampling environment's parameters and analyze data to achieve their goals. The robots with the recovered information will modify and help their own operations smoothly. Such sensors can also be cameras that provide visual information about the environment of the robot. Stereo cameras allow 3D reconstruction and with spatial information provide more accurate and more efficient algorithms. The aim of the task is to create a reconstruction system that includes a space reconstruction algorithm that is able to reconstruct space objects in real time in a 3D way. Accordingly, the article approaches the stereo 3-dimensional reconstruction process initially on a theoretical basis introduced with a matemathical model, then the concepts that are essential to understanding the steps of reconstruction are discussed. A number of tests were produced to demonstrate the algorithm's operation.
{"title":"Stereo Odometry Based Realtime 3D Reconstruction","authors":"Máté Tóth, D. Stojcsics, Zsolt Domozi, I. Lovas","doi":"10.1109/SISY.2018.8524616","DOIUrl":"https://doi.org/10.1109/SISY.2018.8524616","url":null,"abstract":"Nowadays the autonomous robots are spreading more widely, meanwhile the people can meet such devices in everyday life, which can do different tasks independently. The robots are equipped with sensors to sampling environment's parameters and analyze data to achieve their goals. The robots with the recovered information will modify and help their own operations smoothly. Such sensors can also be cameras that provide visual information about the environment of the robot. Stereo cameras allow 3D reconstruction and with spatial information provide more accurate and more efficient algorithms. The aim of the task is to create a reconstruction system that includes a space reconstruction algorithm that is able to reconstruct space objects in real time in a 3D way. Accordingly, the article approaches the stereo 3-dimensional reconstruction process initially on a theoretical basis introduced with a matemathical model, then the concepts that are essential to understanding the steps of reconstruction are discussed. A number of tests were produced to demonstrate the algorithm's operation.","PeriodicalId":6647,"journal":{"name":"2018 IEEE 16th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"15 1","pages":"000321-000326"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81500522","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 : 2018-09-01DOI: 10.1109/SISY.2018.8524662
Iveta Dirgová Luptáková, Jiri Pospíchal
Community detection is, in principle, a clustering of nodes based typically only on their topological properties that are derived from their positions in the network. Clustering generally uses non-topological information associated with nodes to group them. This paper uses a low-dimensional Euclidean distance of nodes to build a network (i.e. proximity or neighborhood graph) and applies community-based detection for clustering purposes. Nearest neighbors of nodes were connected by edges. Walktrap, edge betweenness, and fast greedy were used for community detection. The proposed approach generally proves superior to basic clustering methods, tested on popular 2D artificial benchmarks, and merits additional study. It also has lower computational complexity than other comparable approaches.
{"title":"Community Detection Based Clustering","authors":"Iveta Dirgová Luptáková, Jiri Pospíchal","doi":"10.1109/SISY.2018.8524662","DOIUrl":"https://doi.org/10.1109/SISY.2018.8524662","url":null,"abstract":"Community detection is, in principle, a clustering of nodes based typically only on their topological properties that are derived from their positions in the network. Clustering generally uses non-topological information associated with nodes to group them. This paper uses a low-dimensional Euclidean distance of nodes to build a network (i.e. proximity or neighborhood graph) and applies community-based detection for clustering purposes. Nearest neighbors of nodes were connected by edges. Walktrap, edge betweenness, and fast greedy were used for community detection. The proposed approach generally proves superior to basic clustering methods, tested on popular 2D artificial benchmarks, and merits additional study. It also has lower computational complexity than other comparable approaches.","PeriodicalId":6647,"journal":{"name":"2018 IEEE 16th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"31 1","pages":"000289-000294"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85267076","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 : 2018-09-01DOI: 10.1109/SISY.2018.8524833
T. Došenović, D. Rakic, A. Takaci
Generalization of the Banach contraction principle by the use of the integral type of contraction is given in the Branciari paper. In this paper we prove fixed point results for multivalued mappings using a more generalized contractive condition.
{"title":"Integral Contraction and Fixed Point Results","authors":"T. Došenović, D. Rakic, A. Takaci","doi":"10.1109/SISY.2018.8524833","DOIUrl":"https://doi.org/10.1109/SISY.2018.8524833","url":null,"abstract":"Generalization of the Banach contraction principle by the use of the integral type of contraction is given in the Branciari paper. In this paper we prove fixed point results for multivalued mappings using a more generalized contractive condition.","PeriodicalId":6647,"journal":{"name":"2018 IEEE 16th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"57 1","pages":"000087-000092"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86518676","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 : 2018-09-01DOI: 10.1109/SISY.2018.8524769
David Janos Feher, Barnabás Sándor
The World's most used Wi-Fi protocol, the WPA2, contained vulnerability and several problems discovered and published by cybersecurity researchers. It has affected the IT World, and further changes can be expected. This article examines the details and effects of this change alongside of user behavior.
{"title":"Effects of the WPA2 KRACK Attack in Real Environment","authors":"David Janos Feher, Barnabás Sándor","doi":"10.1109/SISY.2018.8524769","DOIUrl":"https://doi.org/10.1109/SISY.2018.8524769","url":null,"abstract":"The World's most used Wi-Fi protocol, the WPA2, contained vulnerability and several problems discovered and published by cybersecurity researchers. It has affected the IT World, and further changes can be expected. This article examines the details and effects of this change alongside of user behavior.","PeriodicalId":6647,"journal":{"name":"2018 IEEE 16th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"14 1","pages":"000239-000242"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75261951","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 : 2018-09-01DOI: 10.1109/SISY.2018.8524866
Nataša Duraković, T. Grbic, Sanja Rapajić, Slavica Medić, Sandra Buhmiler
One generalization of the Mellin integral transform in terms of pseudo-analysis is presented in the paper. Basic properties of this type of integral transform and one example are given. Both the g- Mellin convolution and the inverse g- Mellin transform are defined. The connections among the g- Mellin transform, the g- Mellin convolution and the inverse g- Mellin transform and the Mellin transform, as well as the connection between the Mellin convolution and the inverse Mellin transform are presented.
{"title":"g-Mellin Transform","authors":"Nataša Duraković, T. Grbic, Sanja Rapajić, Slavica Medić, Sandra Buhmiler","doi":"10.1109/SISY.2018.8524866","DOIUrl":"https://doi.org/10.1109/SISY.2018.8524866","url":null,"abstract":"One generalization of the Mellin integral transform in terms of pseudo-analysis is presented in the paper. Basic properties of this type of integral transform and one example are given. Both the g- Mellin convolution and the inverse g- Mellin transform are defined. The connections among the g- Mellin transform, the g- Mellin convolution and the inverse g- Mellin transform and the Mellin transform, as well as the connection between the Mellin convolution and the inverse Mellin transform are presented.","PeriodicalId":6647,"journal":{"name":"2018 IEEE 16th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"108 1","pages":"000075-000080"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79217258","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 : 2018-09-01DOI: 10.1109/SISY.2018.8524800
Krisztián Bálint
Terrorism represents an ever-growing danger these days. Regretfully, acts of terrorism have been recurring in an ever-growing number. Due to the rapid development of computer science in the 21st century, it is necessary to find a technical solution enabling the pretermission or prevention of the acts of terror. The unmanned aerial vehicles (UAVs) capable of biometric facial recognition may have a great contribution to the prevention of an eventual act of terror committed by suspicious persons, who jeopardize or end lives of innocent people. In large cities, or during mass happenings, timely identification of the suspicious persons represents a key question of national security. The aim of the present research is to find answers regarding the questions concerning the identification of drones to become efficient and operable. Such a question can be like what kind of battery should be installed on a drone, as this greatly influences flight time. Furthermore, it is important to consider the question of artificial intelligence, as an image taken by a drone is only relevant when it can be rapidly compared with the images of suspicious persons in the database on hand. The article digresses even to what kind of camera should be installed on the UAVs, respectively, the type of the most optimal communication between the user and the vehicle.
{"title":"UAVs with Biometric Facial Recognition Capabilities in the Combat Against Terrorism","authors":"Krisztián Bálint","doi":"10.1109/SISY.2018.8524800","DOIUrl":"https://doi.org/10.1109/SISY.2018.8524800","url":null,"abstract":"Terrorism represents an ever-growing danger these days. Regretfully, acts of terrorism have been recurring in an ever-growing number. Due to the rapid development of computer science in the 21st century, it is necessary to find a technical solution enabling the pretermission or prevention of the acts of terror. The unmanned aerial vehicles (UAVs) capable of biometric facial recognition may have a great contribution to the prevention of an eventual act of terror committed by suspicious persons, who jeopardize or end lives of innocent people. In large cities, or during mass happenings, timely identification of the suspicious persons represents a key question of national security. The aim of the present research is to find answers regarding the questions concerning the identification of drones to become efficient and operable. Such a question can be like what kind of battery should be installed on a drone, as this greatly influences flight time. Furthermore, it is important to consider the question of artificial intelligence, as an image taken by a drone is only relevant when it can be rapidly compared with the images of suspicious persons in the database on hand. The article digresses even to what kind of camera should be installed on the UAVs, respectively, the type of the most optimal communication between the user and the vehicle.","PeriodicalId":6647,"journal":{"name":"2018 IEEE 16th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"871 1","pages":"000185-000190"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76553893","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 : 2018-09-01DOI: 10.1109/SISY.2018.8524697
Zsófia Bodó, B. Lantos
In this paper an improved approach is presented for modeling and control of outdoor quadrotor UAVs. A precise and an approximated dynamic model was elaborated for quadrotors. A hierarchical integrating backstepping control algorithm was constructed that has the capability of handling every effect in the dynamic model and in the meantime successfully ignore the realistic measurement noises. The hierarchical control structure consists of position, attitude and rotor control, extended with path design and state estimation. Control parameters can be easily tuned. The tracking algorithm is able to follow the prescribed path with small error. The sensory system and the state estimation are prepared for outdoor applications. The embedded control system contains a HIL extension to test control algorithms before the first flight under real time conditions. Path tracking results show the effectiveness of the embedded control system.
{"title":"Modeling and Control of Outdoor Quadrotor UAVs","authors":"Zsófia Bodó, B. Lantos","doi":"10.1109/SISY.2018.8524697","DOIUrl":"https://doi.org/10.1109/SISY.2018.8524697","url":null,"abstract":"In this paper an improved approach is presented for modeling and control of outdoor quadrotor UAVs. A precise and an approximated dynamic model was elaborated for quadrotors. A hierarchical integrating backstepping control algorithm was constructed that has the capability of handling every effect in the dynamic model and in the meantime successfully ignore the realistic measurement noises. The hierarchical control structure consists of position, attitude and rotor control, extended with path design and state estimation. Control parameters can be easily tuned. The tracking algorithm is able to follow the prescribed path with small error. The sensory system and the state estimation are prepared for outdoor applications. The embedded control system contains a HIL extension to test control algorithms before the first flight under real time conditions. Path tracking results show the effectiveness of the embedded control system.","PeriodicalId":6647,"journal":{"name":"2018 IEEE 16th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"50 1","pages":"000111-000116"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89243154","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 : 2018-09-01DOI: 10.1109/SISY.2018.8524670
E. Nyaguly, D. Simoiu, I. Crâstiu, Calin Pop-Gozman, D. Vlădaia, L. Bereteu
Paint coating of metal surfaces has the purpose not only to increase the aesthetic value but also to provide anticorrosive protection, and improve the mechanical qualities. The life of a paint coating depends on the adhesion between the two materials, the substrate and the paint. At the boundary of separation between the two materials, in the bending process, a jump of the bending effort occurs, which results in a shear stress. This stress depends on the elasticity of the two materials, but also on the thickness of the deposited layer. It is therefore important to be able to determine the thickness of the paint layer. Based on the analysis of the bending vibrations of a sample, before and after coating with paint using the Bernoulli equation, a ratio of natural frequencies is determined as a function of the elasticity modules of the two materials, their densities and their geometric dimensions. From this ratio can be determined the thickness of the paint layer knowing the natural vibration frequencies. The proposed method is nondestructive and is based on the analysis of vibration signals obtained by impulse excitation of samples, before and after coating with paint. By applying the Fast Fourier Transform (FFT), natural frequencies are obtained in the two situations. The experimental results come to validate numerical results obtained by applying the Finite Element Analysis (FEA).
{"title":"Determination of the Thickness of the Paint Coating of Metal Surfaces by the Impulse Technique","authors":"E. Nyaguly, D. Simoiu, I. Crâstiu, Calin Pop-Gozman, D. Vlădaia, L. Bereteu","doi":"10.1109/SISY.2018.8524670","DOIUrl":"https://doi.org/10.1109/SISY.2018.8524670","url":null,"abstract":"Paint coating of metal surfaces has the purpose not only to increase the aesthetic value but also to provide anticorrosive protection, and improve the mechanical qualities. The life of a paint coating depends on the adhesion between the two materials, the substrate and the paint. At the boundary of separation between the two materials, in the bending process, a jump of the bending effort occurs, which results in a shear stress. This stress depends on the elasticity of the two materials, but also on the thickness of the deposited layer. It is therefore important to be able to determine the thickness of the paint layer. Based on the analysis of the bending vibrations of a sample, before and after coating with paint using the Bernoulli equation, a ratio of natural frequencies is determined as a function of the elasticity modules of the two materials, their densities and their geometric dimensions. From this ratio can be determined the thickness of the paint layer knowing the natural vibration frequencies. The proposed method is nondestructive and is based on the analysis of vibration signals obtained by impulse excitation of samples, before and after coating with paint. By applying the Fast Fourier Transform (FFT), natural frequencies are obtained in the two situations. The experimental results come to validate numerical results obtained by applying the Finite Element Analysis (FEA).","PeriodicalId":6647,"journal":{"name":"2018 IEEE 16th International Symposium on Intelligent Systems and Informatics (SISY)","volume":"77 1","pages":"000133-000136"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85143804","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：