Pub Date : 2019-09-01DOI: 10.1109/SYNASC49474.2019.00055
Kristijan Cincar, Todor Ivascu
This work presents an intelligent hospital management system for medical personnel and patients scheduling. In response to the dynamic changing environment, the system must be capable to continuously adjust the schedules. We propose a multi-agent architecture that can handle these issues. Different hospital concepts, medical personnel, patients and other hospital resources were modeled as agents. We stated that such a system would substantially reduce the waiting time in medical institutions by managing resources more efficiently.
{"title":"Agent-Based Hospital Scheduling System","authors":"Kristijan Cincar, Todor Ivascu","doi":"10.1109/SYNASC49474.2019.00055","DOIUrl":"https://doi.org/10.1109/SYNASC49474.2019.00055","url":null,"abstract":"This work presents an intelligent hospital management system for medical personnel and patients scheduling. In response to the dynamic changing environment, the system must be capable to continuously adjust the schedules. We propose a multi-agent architecture that can handle these issues. Different hospital concepts, medical personnel, patients and other hospital resources were modeled as agents. We stated that such a system would substantially reduce the waiting time in medical institutions by managing resources more efficiently.","PeriodicalId":102054,"journal":{"name":"2019 21st International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127704918","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 : 2019-09-01DOI: 10.1109/SYNASC49474.2019.00047
Alin-Marius Cruceat, Alexandru Butean
Tracking technologies opened countless opportunities thanks to their non-intrusive way to interact with people, not only defining new levels of entertainment, but also providing significant important data in healthcare, offering treatment through training for people with vision disorders. In this paper we present an approach for helping children with cerebral palsy to adapt to the world and increase their capacity of concentration by enabling them to use Eye Tracking devices without requiring the classic time consuming calibration tests.
{"title":"Assistive Tools for People with Cerebral Palsy: An Eye Tracker Calibration for Vision and Focus Training","authors":"Alin-Marius Cruceat, Alexandru Butean","doi":"10.1109/SYNASC49474.2019.00047","DOIUrl":"https://doi.org/10.1109/SYNASC49474.2019.00047","url":null,"abstract":"Tracking technologies opened countless opportunities thanks to their non-intrusive way to interact with people, not only defining new levels of entertainment, but also providing significant important data in healthcare, offering treatment through training for people with vision disorders. In this paper we present an approach for helping children with cerebral palsy to adapt to the world and increase their capacity of concentration by enabling them to use Eye Tracking devices without requiring the classic time consuming calibration tests.","PeriodicalId":102054,"journal":{"name":"2019 21st International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121033171","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}
With the increase in malware samples in the last decade more antivirus products started to use machine learning algorithms in order to cope with the large volume of data. Thanks to the good results and advances in learning infrastructure the neural networks have become one of the preferred way of addressing this. However, these algorithms need to be fine tuned in order to not add an overhead of costly false positives. This paper presents a study that takes a closer look into two techniques used for false positive mitigation issue: one side training and weight class adjustment. The techniques are used to train a neural network with zero false positives and are compared in order to find out which one give the highest true positive rate. Using a large dataset constructed over several years we show that by using these techniques a 90% true positive rate can be obtained while training for 0 false positives.
{"title":"Methods for Training Neural Networks with Zero False Positives for Malware Detection","authors":"Dan-Georgian Marculet, Razvan Benchea, Dragos Gavrilut","doi":"10.1109/SYNASC49474.2019.00039","DOIUrl":"https://doi.org/10.1109/SYNASC49474.2019.00039","url":null,"abstract":"With the increase in malware samples in the last decade more antivirus products started to use machine learning algorithms in order to cope with the large volume of data. Thanks to the good results and advances in learning infrastructure the neural networks have become one of the preferred way of addressing this. However, these algorithms need to be fine tuned in order to not add an overhead of costly false positives. This paper presents a study that takes a closer look into two techniques used for false positive mitigation issue: one side training and weight class adjustment. The techniques are used to train a neural network with zero false positives and are compared in order to find out which one give the highest true positive rate. Using a large dataset constructed over several years we show that by using these techniques a 90% true positive rate can be obtained while training for 0 false positives.","PeriodicalId":102054,"journal":{"name":"2019 21st International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130243996","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 : 2019-09-01DOI: 10.1109/SYNASC49474.2019.00050
A. Petruşel, R. Truşcă
The purpose of this work is to present some fixed point results, based on iteration methods, for some classes of non-self mappings. We will consider the following classes: contractions, Berinde type contractions, graphic contractions and Hardy-Rogers type contractions.
{"title":"Iterative Approximations for Non-Self Operators","authors":"A. Petruşel, R. Truşcă","doi":"10.1109/SYNASC49474.2019.00050","DOIUrl":"https://doi.org/10.1109/SYNASC49474.2019.00050","url":null,"abstract":"The purpose of this work is to present some fixed point results, based on iteration methods, for some classes of non-self mappings. We will consider the following classes: contractions, Berinde type contractions, graphic contractions and Hardy-Rogers type contractions.","PeriodicalId":102054,"journal":{"name":"2019 21st International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125556451","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 : 2019-09-01DOI: 10.1109/SYNASC49474.2019.00008
A. Andreica
Cellular Automata have been used as tools for solving tasks from different areas, in the bigger context of finding local interaction rules that give rise to a certain global behaviour.
元胞自动机已被用作解决来自不同领域的任务的工具，在寻找产生某种全局行为的局部交互规则的更大背景下。
{"title":"Cellular Automata Applications","authors":"A. Andreica","doi":"10.1109/SYNASC49474.2019.00008","DOIUrl":"https://doi.org/10.1109/SYNASC49474.2019.00008","url":null,"abstract":"Cellular Automata have been used as tools for solving tasks from different areas, in the bigger context of finding local interaction rules that give rise to a certain global behaviour.","PeriodicalId":102054,"journal":{"name":"2019 21st International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","volume":"438 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124254417","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 : 2019-09-01DOI: 10.1109/SYNASC49474.2019.00011
J. Hauenstein
Numerical algebraic geometry provides a toolbox of numerical methods for performing computations involving systems of polynomial equations. Even though some of the computations which are performed on a computer using floating-point arithmetic are not certified, they can often be made very reliable using adaptive precision computations. Moreover, there is a wealth of information regarding the original problem which can be extracted from various numerical computation that can be used to improve subsequent symbolic computations to certify the result. This paper highlights two applications of such hybrid numeric-symbolic methods in algebraic geometry.
{"title":"Using Numerical Insights to Improve Symbolic Computations","authors":"J. Hauenstein","doi":"10.1109/SYNASC49474.2019.00011","DOIUrl":"https://doi.org/10.1109/SYNASC49474.2019.00011","url":null,"abstract":"Numerical algebraic geometry provides a toolbox of numerical methods for performing computations involving systems of polynomial equations. Even though some of the computations which are performed on a computer using floating-point arithmetic are not certified, they can often be made very reliable using adaptive precision computations. Moreover, there is a wealth of information regarding the original problem which can be extracted from various numerical computation that can be used to improve subsequent symbolic computations to certify the result. This paper highlights two applications of such hybrid numeric-symbolic methods in algebraic geometry.","PeriodicalId":102054,"journal":{"name":"2019 21st International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134346579","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 : 2019-09-01DOI: 10.1109/SYNASC49474.2019.00049
Alexandru Munteanu, Teodora Selea, Marian Neagul
In this paper we investigate state of the art deep learning model topologies applied to the problem of semantic segmentation, particularly for extracting road segments in satellite images. In our experiments we used Pan-Sharpened RGB input data from the SpaceNet Roads Dataset, analyzed U-Net, SegNet and ResNet model performance and investigate how different loss functions affect the model performance.
{"title":"Deep Learning Techniques Applied for Road Segmentation","authors":"Alexandru Munteanu, Teodora Selea, Marian Neagul","doi":"10.1109/SYNASC49474.2019.00049","DOIUrl":"https://doi.org/10.1109/SYNASC49474.2019.00049","url":null,"abstract":"In this paper we investigate state of the art deep learning model topologies applied to the problem of semantic segmentation, particularly for extracting road segments in satellite images. In our experiments we used Pan-Sharpened RGB input data from the SpaceNet Roads Dataset, analyzed U-Net, SegNet and ResNet model performance and investigate how different loss functions affect the model performance.","PeriodicalId":102054,"journal":{"name":"2019 21st International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116305525","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 : 2019-09-01DOI: 10.1109/synasc49474.2019.00007
D. J. Jeffrey, Wen-Shin Lee, Mircea Marin, C. Bǎdicǎ, A. Florea, V. Negru
Logic and Programming Stefan Andrei, Lamar University, USA Sebastien Bardin, CEA LIST, France Constantin Enea, IRIF, Université Paris Diderot, France Madalina Erascu, IeAT and West University of Timisoara, Romania Cezary Kaliszyk, RISC-Linz, Austria Benjamin Kiesl, CISPA Helmholts Center, Germany Boris Konev, University of Liverpool, UK Gergely Kovasznai, Eszterházy Károly University, Eger, Hungary Temur Kutsia, Research Institute for Symbolic Computation, Austria Dorel Lucanu, Alexandru Ioan Cuza University, Romania Kuldeep Meel, National University of Singapore Zvonimir Rakamaric, University of Utah, USA Viorica Sofronie-Stokkermans, University Koblenz-Landau, Germany Ana Sokolova, University of Salzburg, Austria Sorin Stratulat, Université de Lorraine, Metz, France Martin Suda, Czech University of Technology, Austria Alexander Summers, ETH Zurich, Switzerland Jun Sun, National University of Singapore Tjark Weber, Uppsala University, Sweden Damien Zufferey, MPI-SWS, Germany
{"title":"SYNASC 2019 Program Committees","authors":"D. J. Jeffrey, Wen-Shin Lee, Mircea Marin, C. Bǎdicǎ, A. Florea, V. Negru","doi":"10.1109/synasc49474.2019.00007","DOIUrl":"https://doi.org/10.1109/synasc49474.2019.00007","url":null,"abstract":"Logic and Programming Stefan Andrei, Lamar University, USA Sebastien Bardin, CEA LIST, France Constantin Enea, IRIF, Université Paris Diderot, France Madalina Erascu, IeAT and West University of Timisoara, Romania Cezary Kaliszyk, RISC-Linz, Austria Benjamin Kiesl, CISPA Helmholts Center, Germany Boris Konev, University of Liverpool, UK Gergely Kovasznai, Eszterházy Károly University, Eger, Hungary Temur Kutsia, Research Institute for Symbolic Computation, Austria Dorel Lucanu, Alexandru Ioan Cuza University, Romania Kuldeep Meel, National University of Singapore Zvonimir Rakamaric, University of Utah, USA Viorica Sofronie-Stokkermans, University Koblenz-Landau, Germany Ana Sokolova, University of Salzburg, Austria Sorin Stratulat, Université de Lorraine, Metz, France Martin Suda, Czech University of Technology, Austria Alexander Summers, ETH Zurich, Switzerland Jun Sun, National University of Singapore Tjark Weber, Uppsala University, Sweden Damien Zufferey, MPI-SWS, Germany","PeriodicalId":102054,"journal":{"name":"2019 21st International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126410500","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 : 2019-09-01DOI: 10.1109/SYNASC49474.2019.00020
D. Copandean, D. Gorgan
Asteroid discovery is not an activity restricted to the notable surveying efforts that have their private staff, equipment and detection programs, but it is also popular among amateurs and various mini-surveys. In light of this situation, new Near Earth Asteroids (NEAs) are found out every day. Most of the amateurs and mini-surveys discoveries are obtained by means of manual methods, based on the human eye examination of celestial image data. Naturally, these methods are limited by the size and complexity of the input data. To address the issues linked to such dimensional data, we developed under the NEARBY project an automated pipeline prototype for asteroid detection. This solution comes in the form of a modular system, allowing us to explore different detection techniques. Throughout this paper a visual technique, based on image processing will be presented as a possible future replacement for the current technique used now in NEARBY pipeline, the astronomical solution based on computation in the celestial reference system.
{"title":"A Visual Solution in Asteroids Detection","authors":"D. Copandean, D. Gorgan","doi":"10.1109/SYNASC49474.2019.00020","DOIUrl":"https://doi.org/10.1109/SYNASC49474.2019.00020","url":null,"abstract":"Asteroid discovery is not an activity restricted to the notable surveying efforts that have their private staff, equipment and detection programs, but it is also popular among amateurs and various mini-surveys. In light of this situation, new Near Earth Asteroids (NEAs) are found out every day. Most of the amateurs and mini-surveys discoveries are obtained by means of manual methods, based on the human eye examination of celestial image data. Naturally, these methods are limited by the size and complexity of the input data. To address the issues linked to such dimensional data, we developed under the NEARBY project an automated pipeline prototype for asteroid detection. This solution comes in the form of a modular system, allowing us to explore different detection techniques. Throughout this paper a visual technique, based on image processing will be presented as a possible future replacement for the current technique used now in NEARBY pipeline, the astronomical solution based on computation in the celestial reference system.","PeriodicalId":102054,"journal":{"name":"2019 21st International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132862125","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 : 2019-09-01DOI: 10.1109/SYNASC49474.2019.00030
Ioan Sima, B. Pârv
The Whale Optimization Algorithm (WOA) is a novel nature-inspired algorithm, being originally dedicated to continuous function optimization. This paper modifies it to address combinatorial, i.e. discrete function optimization; the new algorithm is called Combinatorial Whale Optimization Algorithm (cWOA). cWOA was applied to protein folding problem on the 2D HP Model, which is a well known combinatorial optimization problem. The results are encouraging for further development and expansion of experiments to 3D HP or other models.
{"title":"Protein Folding Simulation Using Combinatorial Whale Optimization Algorithm","authors":"Ioan Sima, B. Pârv","doi":"10.1109/SYNASC49474.2019.00030","DOIUrl":"https://doi.org/10.1109/SYNASC49474.2019.00030","url":null,"abstract":"The Whale Optimization Algorithm (WOA) is a novel nature-inspired algorithm, being originally dedicated to continuous function optimization. This paper modifies it to address combinatorial, i.e. discrete function optimization; the new algorithm is called Combinatorial Whale Optimization Algorithm (cWOA). cWOA was applied to protein folding problem on the 2D HP Model, which is a well known combinatorial optimization problem. The results are encouraging for further development and expansion of experiments to 3D HP or other models.","PeriodicalId":102054,"journal":{"name":"2019 21st International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134222502","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：