Pub Date : 2019-07-01DOI: 10.1109/IISA.2019.8900732
Stamatia Triantopoulou, Dimitrios Papanikas, P. Kotzanikolaou
This paper presents an experimental analysis of current Distributed Denial of Service attacks. Our analysis is based on real data collected by a honeynet system that was installed on an ISP edge router, for a four-month period. In the examined scenario, we identify and analyze malicious activities based on packets captured and analyzed by a network protocol sniffer and signature-based attack analysis tools. Our analysis shows that IoT-based DDoS attacks are one of the latest and most proliferating attack trends in network security. Based on the analysis of the attacks, we describe some mitigation techniques that can be applied at the providers’ network to mitigate the trending attack vectors.
{"title":"An Experimental Analysis of Current DDoS attacks Based on a Provider Edge Router Honeynet","authors":"Stamatia Triantopoulou, Dimitrios Papanikas, P. Kotzanikolaou","doi":"10.1109/IISA.2019.8900732","DOIUrl":"https://doi.org/10.1109/IISA.2019.8900732","url":null,"abstract":"This paper presents an experimental analysis of current Distributed Denial of Service attacks. Our analysis is based on real data collected by a honeynet system that was installed on an ISP edge router, for a four-month period. In the examined scenario, we identify and analyze malicious activities based on packets captured and analyzed by a network protocol sniffer and signature-based attack analysis tools. Our analysis shows that IoT-based DDoS attacks are one of the latest and most proliferating attack trends in network security. Based on the analysis of the attacks, we describe some mitigation techniques that can be applied at the providers’ network to mitigate the trending attack vectors.","PeriodicalId":371385,"journal":{"name":"2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124410306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/IISA.2019.8900756
Jongkuk Park, Y. Yoon, Jahng-Hyeon Park
This paper clarifies an issue that the most commonly used ADAS sensors, monocular camera and radar, do not provide abundant information about dynamically changing road scenes. In order to make the sensor more useful for a wide range of ADAS functions, we present an approach to estimate the orientation of surrounding vehicles using deep neural network. We show the possibility that camera-based method can get more competitive, evaluating it on the KITTI Orientation Estimation Benchmark, and also verifying it on our test-driving scenarios. Although its localization performance is not perfect, our model is able to reliably predict the orientation when fine conditions are given. In addition, we further study on training models using synthetic dataset, and share the weakness of this method when comparing to LiDAR-based approach on several conditions such as fully-visible, lightly/heavily-occluded and shading/lighting circumstances.
{"title":"Deep Learning-Based Vehicle Orientation Estimation with Analysis of Training Models on Virtual-Worlds","authors":"Jongkuk Park, Y. Yoon, Jahng-Hyeon Park","doi":"10.1109/IISA.2019.8900756","DOIUrl":"https://doi.org/10.1109/IISA.2019.8900756","url":null,"abstract":"This paper clarifies an issue that the most commonly used ADAS sensors, monocular camera and radar, do not provide abundant information about dynamically changing road scenes. In order to make the sensor more useful for a wide range of ADAS functions, we present an approach to estimate the orientation of surrounding vehicles using deep neural network. We show the possibility that camera-based method can get more competitive, evaluating it on the KITTI Orientation Estimation Benchmark, and also verifying it on our test-driving scenarios. Although its localization performance is not perfect, our model is able to reliably predict the orientation when fine conditions are given. In addition, we further study on training models using synthetic dataset, and share the weakness of this method when comparing to LiDAR-based approach on several conditions such as fully-visible, lightly/heavily-occluded and shading/lighting circumstances.","PeriodicalId":371385,"journal":{"name":"2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129776044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/IISA.2019.8900781
Giorgos Papoulias, Stavros Nousias, K. Moustakas
In recent years, fluid-structure interaction (FSI) methods are increasingly used for expanding our knowledge of blood flow’s characteristics and inherent tendencies as well as their impact on the morphological alterations of vessel wall tissues. The current study attempts to provide a simulation framework and a visualization tool which will fuel the potential to model deformations of the cerebral aneurysm vessel wall and identify intense wall displacements, highlighting regions with an increased possibility of rupture. The fluid-structure interaction method modelled by our approach is a two-step iterative process comprised of a fluid dynamics simulation step and a finite element method based deformation step simulating and visualizing the blood vessel wall deformation for a complete cardiac cycle.
{"title":"Fluid-structure interaction simulation framework for cerebral aneurysm wall deformation","authors":"Giorgos Papoulias, Stavros Nousias, K. Moustakas","doi":"10.1109/IISA.2019.8900781","DOIUrl":"https://doi.org/10.1109/IISA.2019.8900781","url":null,"abstract":"In recent years, fluid-structure interaction (FSI) methods are increasingly used for expanding our knowledge of blood flow’s characteristics and inherent tendencies as well as their impact on the morphological alterations of vessel wall tissues. The current study attempts to provide a simulation framework and a visualization tool which will fuel the potential to model deformations of the cerebral aneurysm vessel wall and identify intense wall displacements, highlighting regions with an increased possibility of rupture. The fluid-structure interaction method modelled by our approach is a two-step iterative process comprised of a fluid dynamics simulation step and a finite element method based deformation step simulating and visualizing the blood vessel wall deformation for a complete cardiac cycle.","PeriodicalId":371385,"journal":{"name":"2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126759113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/IISA.2019.8900740
Konstantinos Giannakis, Christos Papalitsas, Georgia Theocharopoulou, Sofia Fanarioti, T. Andronikos
Data related to biology are characterized by large volume and requirements for enormous computational power. Biological sequences, either of proteins or DNA/RNA segments, can be large and usually need massive computations in order to discover relations and study particular properties. Aligning sequences is of great importance for various practical reasons. Multiple sequence alignment studies the problem of aligning several strings resulting in a complete alignment, a problem for which several different approaches exist. In this work, a novel heuristic method to progressively solve this problem is proposed using elements of quantum-inspired optimization. The proposed algorithm is described in detail and evaluated through simulations against other aligning methods. The experimental results seem promising for providing a good initial alignment, especially for the case of large sets of sequences.
{"title":"A Quantum-inspired optimization Heuristic for the Multiple Sequence Alignment Problem in Bio-computing","authors":"Konstantinos Giannakis, Christos Papalitsas, Georgia Theocharopoulou, Sofia Fanarioti, T. Andronikos","doi":"10.1109/IISA.2019.8900740","DOIUrl":"https://doi.org/10.1109/IISA.2019.8900740","url":null,"abstract":"Data related to biology are characterized by large volume and requirements for enormous computational power. Biological sequences, either of proteins or DNA/RNA segments, can be large and usually need massive computations in order to discover relations and study particular properties. Aligning sequences is of great importance for various practical reasons. Multiple sequence alignment studies the problem of aligning several strings resulting in a complete alignment, a problem for which several different approaches exist. In this work, a novel heuristic method to progressively solve this problem is proposed using elements of quantum-inspired optimization. The proposed algorithm is described in detail and evaluated through simulations against other aligning methods. The experimental results seem promising for providing a good initial alignment, especially for the case of large sets of sequences.","PeriodicalId":371385,"journal":{"name":"2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125720584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/IISA.2019.8900717
K. Antonopoulos, C. Panagiotou, Christos P. Antonopoulos, N. Voros
Precision farming comprises one of the most rapidly evolving research and development areas, attracting high interest by both the industry as well as the academia. However, for respective systems to be practical and deliver significant benefits, many breakthroughs must be materialized. One of the most critical is the development of efficient, flexible, extendable and reliable Cyber Physical System (CPS) platforms. Therefore, in this paper such a complete, commercial grade architecture is presented, able to meet the requirements of multifaceted demanding agricultural cultivation deployments. The proposed solution can be utilized in any type of cultivation, anticipating significant benefits in metrics such as minimization of water wastage, and chemical fertilizer usage.
{"title":"A-FARM Precision Farming CPS Platform","authors":"K. Antonopoulos, C. Panagiotou, Christos P. Antonopoulos, N. Voros","doi":"10.1109/IISA.2019.8900717","DOIUrl":"https://doi.org/10.1109/IISA.2019.8900717","url":null,"abstract":"Precision farming comprises one of the most rapidly evolving research and development areas, attracting high interest by both the industry as well as the academia. However, for respective systems to be practical and deliver significant benefits, many breakthroughs must be materialized. One of the most critical is the development of efficient, flexible, extendable and reliable Cyber Physical System (CPS) platforms. Therefore, in this paper such a complete, commercial grade architecture is presented, able to meet the requirements of multifaceted demanding agricultural cultivation deployments. The proposed solution can be utilized in any type of cultivation, anticipating significant benefits in metrics such as minimization of water wastage, and chemical fertilizer usage.","PeriodicalId":371385,"journal":{"name":"2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132709066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/IISA.2019.8900684
A. Panagiotopoulou, E. Charou, M. Stefouli, K. Platis, N. Madamopoulos, E. Bratsolis
This work super-resolves the lowest-resolution 60m/pixel Sentinel-2 B1 and B9 to the highest-resolution 10m/pixel. Two different categories of super-resolution (SR) techniques are utilized, in specific a SR technique which performs information transfer among different bands and the stochastic regularized SR technique Var-norm+BTV. The study area is the Lysimachia Lake, Western Greece. The Sentinel-2 image of 10th November 2018 has been selected to test the different techniques.
{"title":"Sentinel-2 “low resolution band” optimization using Super-Resolution techniques:Lysimachia Lake pilot area of analysis","authors":"A. Panagiotopoulou, E. Charou, M. Stefouli, K. Platis, N. Madamopoulos, E. Bratsolis","doi":"10.1109/IISA.2019.8900684","DOIUrl":"https://doi.org/10.1109/IISA.2019.8900684","url":null,"abstract":"This work super-resolves the lowest-resolution 60m/pixel Sentinel-2 B1 and B9 to the highest-resolution 10m/pixel. Two different categories of super-resolution (SR) techniques are utilized, in specific a SR technique which performs information transfer among different bands and the stochastic regularized SR technique Var-norm+BTV. The study area is the Lysimachia Lake, Western Greece. The Sentinel-2 image of 10th November 2018 has been selected to test the different techniques.","PeriodicalId":371385,"journal":{"name":"2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132065107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/IISA.2019.8900752
Konstantinos Annousakis-Giannakopoulos, D. Ampeliotis, A. Skodras
With the development of computer graphics rendering software, it has become extremely difficult to distinguish whether an image is computer generated or a natural one. Therefore, it is really important to device robust methods for correctly classifying these two categories of images. In this work, a new approach to face the above problem is developed that is based upon the discrete cosine transform (DCT) of an image, in the YCbCr color space. The statistical features extracted, have been tested in suitable databases and the remarkable results indicate that the proposed model has a great potential to be used in digital images forensics.
{"title":"Could DCT Reveal Photorealistic Images?","authors":"Konstantinos Annousakis-Giannakopoulos, D. Ampeliotis, A. Skodras","doi":"10.1109/IISA.2019.8900752","DOIUrl":"https://doi.org/10.1109/IISA.2019.8900752","url":null,"abstract":"With the development of computer graphics rendering software, it has become extremely difficult to distinguish whether an image is computer generated or a natural one. Therefore, it is really important to device robust methods for correctly classifying these two categories of images. In this work, a new approach to face the above problem is developed that is based upon the discrete cosine transform (DCT) of an image, in the YCbCr color space. The statistical features extracted, have been tested in suitable databases and the remarkable results indicate that the proposed model has a great potential to be used in digital images forensics.","PeriodicalId":371385,"journal":{"name":"2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115453170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/IISA.2019.8900734
Jaime D. L. Caro, Jose Mari H. Catipay, Michael Jason Y. Benedicto, Kei O. Shirabe, Michael T. Garcia, M. Tee, E. Aguilar
The health of farmers has potential effects on productivity. Applying the One Health approach takes consideration of the farmer’s work environment in assessing the health of the farmer. Studies have shown that improper handling of pesticides in the Philippines may lead to unforeseen health risks to our farmers. With the use of an application where farmers can monitor their personal health and work environment, particularly their pesticide use, medical professionals and policy makers can use the data to get a glimpse of the effects of chemical use to our farmers’ health.
{"title":"Monitoring Application for Farmer Pesticide Use","authors":"Jaime D. L. Caro, Jose Mari H. Catipay, Michael Jason Y. Benedicto, Kei O. Shirabe, Michael T. Garcia, M. Tee, E. Aguilar","doi":"10.1109/IISA.2019.8900734","DOIUrl":"https://doi.org/10.1109/IISA.2019.8900734","url":null,"abstract":"The health of farmers has potential effects on productivity. Applying the One Health approach takes consideration of the farmer’s work environment in assessing the health of the farmer. Studies have shown that improper handling of pesticides in the Philippines may lead to unforeseen health risks to our farmers. With the use of an application where farmers can monitor their personal health and work environment, particularly their pesticide use, medical professionals and policy makers can use the data to get a glimpse of the effects of chemical use to our farmers’ health.","PeriodicalId":371385,"journal":{"name":"2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114429803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/IISA.2019.8900741
Georgios S. Temponeras, Stamatios-Aggelos N. Alexandropoulos, S. Kotsiantis, M. Vrahatis
A very important issue in the financial field is to identify and reliably predict Fraudulent Financial Statements (FFS). For this purpose, several Machine Learning models have been developed that identify the issues that are directly related to FFS. In this paper, we present a new predictive model for fraudulent detection through a deep dense artificial neural network. Specifically, a new forecasting model was tested experimentally using data from Greek companies. The obtained results showed that the proposed scheme is robust and promising.
{"title":"Financial Fraudulent Statements Detection through a Deep Dense Artificial Neural Network","authors":"Georgios S. Temponeras, Stamatios-Aggelos N. Alexandropoulos, S. Kotsiantis, M. Vrahatis","doi":"10.1109/IISA.2019.8900741","DOIUrl":"https://doi.org/10.1109/IISA.2019.8900741","url":null,"abstract":"A very important issue in the financial field is to identify and reliably predict Fraudulent Financial Statements (FFS). For this purpose, several Machine Learning models have been developed that identify the issues that are directly related to FFS. In this paper, we present a new predictive model for fraudulent detection through a deep dense artificial neural network. Specifically, a new forecasting model was tested experimentally using data from Greek companies. The obtained results showed that the proposed scheme is robust and promising.","PeriodicalId":371385,"journal":{"name":"2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130938303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/IISA.2019.8900679
Efstathios Branikas, Thomas Papastergiou, E. Zacharaki, V. Megalooikonomou
As the amount of data increases, fully supervised learning methods relying on dense annotations often become impractical, and are substituted by weakly supervised methods, that exploit data with a variable content in respect to size and semantics. In such schemes the volume of irrelevant information might be critically high impacting negatively the modeling performance and increasing considerably the memory and computational cost. Data reduction or selection are necessary to mitigate these effects. In this paper we propose and compare three different instance selection techniques for the Multiple Instance Learning (MIL) paradigm. The techniques are assessed for the problem of image classification using features from standard benchmark MIL datasets, as well as recently proposed features based on tensor decomposition. As implementation paradigm we exploit the widely accepted JC2MIL algorithm that performs joint clustering and classification. Two of the proposed instance selection techniques are based on Shannon entropy in image and feature space respectively, while one technique is based on a clustering evaluation metric, the silhouette score, that is introduced internally in the iterative joint clustering and classification algorithm. The enrichment of the MIL framework with the instance selection step showed to outperform the original algorithm providing state-of-the-art results in the vast majority of the performed experiments.
{"title":"Instance Selection Techniques for Multiple Instance Classification","authors":"Efstathios Branikas, Thomas Papastergiou, E. Zacharaki, V. Megalooikonomou","doi":"10.1109/IISA.2019.8900679","DOIUrl":"https://doi.org/10.1109/IISA.2019.8900679","url":null,"abstract":"As the amount of data increases, fully supervised learning methods relying on dense annotations often become impractical, and are substituted by weakly supervised methods, that exploit data with a variable content in respect to size and semantics. In such schemes the volume of irrelevant information might be critically high impacting negatively the modeling performance and increasing considerably the memory and computational cost. Data reduction or selection are necessary to mitigate these effects. In this paper we propose and compare three different instance selection techniques for the Multiple Instance Learning (MIL) paradigm. The techniques are assessed for the problem of image classification using features from standard benchmark MIL datasets, as well as recently proposed features based on tensor decomposition. As implementation paradigm we exploit the widely accepted JC2MIL algorithm that performs joint clustering and classification. Two of the proposed instance selection techniques are based on Shannon entropy in image and feature space respectively, while one technique is based on a clustering evaluation metric, the silhouette score, that is introduced internally in the iterative joint clustering and classification algorithm. The enrichment of the MIL framework with the instance selection step showed to outperform the original algorithm providing state-of-the-art results in the vast majority of the performed experiments.","PeriodicalId":371385,"journal":{"name":"2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128959569","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：