Bálint Borsos, L. Nagy, David Iclanzan, L. Szilágyi
Abstract According to WHO estimates, 400 million people suffer from diabetes, and this number is likely to double by year 2030. Unfortunately, diabetes can have severe complications like glaucoma or retinopathy, which both can cause blindness. The main goal of our research is to provide an automated procedure that can detect retinopathy-related lesions of the retina from fundus images. This paper focuses on the segmentation of so-called white lesions of the retina that include hard and soft exudates. The established procedure consists of three main phases. The preprocessing step compensates the various luminosity patterns found in retinal images, using background and foreground pixel extraction and a data normalization operator similar to Z-transform. This is followed by a modified SLIC algorithm that provides homogeneous superpixels in the image. The final step is an ANN-based classification of pixels using fifteen features extracted from the neighborhood of the pixels taken from the equalized images and from the properties of the superpixel where the pixel belongs. The proposed methodology was tested using high-resolution fundus images originating from the IDRiD database. Pixelwise accuracy is characterized by a 54% Dice score in average, but the presence of exudates is detected with 94% precision.
{"title":"Automatic detection of hard and soft exudates from retinal fundus images","authors":"Bálint Borsos, L. Nagy, David Iclanzan, L. Szilágyi","doi":"10.2478/ausi-2019-0005","DOIUrl":"https://doi.org/10.2478/ausi-2019-0005","url":null,"abstract":"Abstract According to WHO estimates, 400 million people suffer from diabetes, and this number is likely to double by year 2030. Unfortunately, diabetes can have severe complications like glaucoma or retinopathy, which both can cause blindness. The main goal of our research is to provide an automated procedure that can detect retinopathy-related lesions of the retina from fundus images. This paper focuses on the segmentation of so-called white lesions of the retina that include hard and soft exudates. The established procedure consists of three main phases. The preprocessing step compensates the various luminosity patterns found in retinal images, using background and foreground pixel extraction and a data normalization operator similar to Z-transform. This is followed by a modified SLIC algorithm that provides homogeneous superpixels in the image. The final step is an ANN-based classification of pixels using fifteen features extracted from the neighborhood of the pixels taken from the equalized images and from the properties of the superpixel where the pixel belongs. The proposed methodology was tested using high-resolution fundus images originating from the IDRiD database. Pixelwise accuracy is characterized by a 54% Dice score in average, but the presence of exudates is detected with 94% precision.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"22 1","pages":"65 - 79"},"PeriodicalIF":0.3,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83756987","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}
Abstract In this short survey and case study we want to present our research experience through the project developed by our team, that involves the building of a LEGO MINDSTORMS EV3 robotic arm and tracked robot car which mimics the motion of the human arm and legs. We used 3 interconnected LEGO MINDSTORMS EV3 bricks to reach the desired degrees of freedom. Using a Kinect sensor, the system detects the motion of the human user’s arm and creates the skeletal image of the arm. Coordinate geometry and different approximation methods are used to calculate the rotation angles between the bones connecting the joints. In our project the key is inverse kinematics, whitch makes use of the kinematics equations to determine the joint rotation parameters that provide a desired position for each of the robot’s end-effectors – arms and legs (wheels). The combined motion of the LEGO MINDSTORMS EV3 motors results in a complete robotic forward or backward motion and arm movement which is a perfect mimic of the human arm movement.
{"title":"Gesture-Driven LEGO robots","authors":"Lehel István Kovács","doi":"10.2478/ausi-2019-0006","DOIUrl":"https://doi.org/10.2478/ausi-2019-0006","url":null,"abstract":"Abstract In this short survey and case study we want to present our research experience through the project developed by our team, that involves the building of a LEGO MINDSTORMS EV3 robotic arm and tracked robot car which mimics the motion of the human arm and legs. We used 3 interconnected LEGO MINDSTORMS EV3 bricks to reach the desired degrees of freedom. Using a Kinect sensor, the system detects the motion of the human user’s arm and creates the skeletal image of the arm. Coordinate geometry and different approximation methods are used to calculate the rotation angles between the bones connecting the joints. In our project the key is inverse kinematics, whitch makes use of the kinematics equations to determine the joint rotation parameters that provide a desired position for each of the robot’s end-effectors – arms and legs (wheels). The combined motion of the LEGO MINDSTORMS EV3 motors results in a complete robotic forward or backward motion and arm movement which is a perfect mimic of the human arm movement.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"88 1","pages":"80 - 94"},"PeriodicalIF":0.3,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79689608","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}
J. Sebastian, J. V. Kureethara, S. Naduvath, C. Dominic
Abstract A path decomposition of a graph is a collection of its edge disjoint paths whose union is G. The pendant number Πp is the minimum number of end vertices of paths in a path decomposition of G. In this paper, we determine the pendant number of corona products and rooted products of paths and cycles and obtain some bounds for the pendant number for some specific derived graphs. Further, for any natural number n, the existence of a connected graph with pendant number n has also been established.
{"title":"A study on the pendant number of graph products","authors":"J. Sebastian, J. V. Kureethara, S. Naduvath, C. Dominic","doi":"10.2478/ausi-2019-0002","DOIUrl":"https://doi.org/10.2478/ausi-2019-0002","url":null,"abstract":"Abstract A path decomposition of a graph is a collection of its edge disjoint paths whose union is G. The pendant number Πp is the minimum number of end vertices of paths in a path decomposition of G. In this paper, we determine the pendant number of corona products and rooted products of paths and cycles and obtain some bounds for the pendant number for some specific derived graphs. Further, for any natural number n, the existence of a connected graph with pendant number n has also been established.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"16 1","pages":"24 - 40"},"PeriodicalIF":0.3,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73015638","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}
Abstract A set of vertices in a graph is a dominating set if every vertex not in the set is adjacent to at least one vertex in the set. A dominating structure is a subgraph induced by the dominating set. Connected domination is a type of domination where the dominating structure is connected. Clique domination is a type of domination in graphs where the dominating structure is a complete subgraph. The clique domination number of a graph G denoted by γk(G) is the minimum cardinality among all the clique dominating sets of G. We present few properties of graphs admitting dominating cliques along with bounds on clique domination number in terms of order and size of the graph. A necessary and sufficient condition for the existence of dominating clique in strong product of graphs is presented. A forbidden subgraph condition necessary to imply the existence of a connected dominating set of size four also is found.
{"title":"New results on connected dominating structures in graphs","authors":"Libin Chacko Samuel, Mayamma Joseph","doi":"10.2478/ausi-2019-0004","DOIUrl":"https://doi.org/10.2478/ausi-2019-0004","url":null,"abstract":"Abstract A set of vertices in a graph is a dominating set if every vertex not in the set is adjacent to at least one vertex in the set. A dominating structure is a subgraph induced by the dominating set. Connected domination is a type of domination where the dominating structure is connected. Clique domination is a type of domination in graphs where the dominating structure is a complete subgraph. The clique domination number of a graph G denoted by γk(G) is the minimum cardinality among all the clique dominating sets of G. We present few properties of graphs admitting dominating cliques along with bounds on clique domination number in terms of order and size of the graph. A necessary and sufficient condition for the existence of dominating clique in strong product of graphs is presented. A forbidden subgraph condition necessary to imply the existence of a connected dominating set of size four also is found.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"106 1","pages":"52 - 64"},"PeriodicalIF":0.3,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77686338","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}
Abstract Current climate models are complex computer programs that are typically iterated time-step by time-step to predict the next set of values of the climate-related variables. Since these iterative methods are necessarily computed only for a fixed number of iterations, they are unable to answer the natural question whether there is a limit to the rise of global temperature. In order to answer that question we propose to combine climate models with software verification techniques that can find invariant conditions for the set of program variables. In particular, we apply the constraint database approach to software verification to find that the rise in global temperature is bounded according to the common Java Climate Model that implements the Wigley/Raper Upwelling-Diffusion Energy Balance Model climate model.
{"title":"Estimating the maximum rise in temperature according to climate models using abstract interpretation","authors":"P. Revesz, Robert J. Woodward","doi":"10.2478/ausi-2019-0001","DOIUrl":"https://doi.org/10.2478/ausi-2019-0001","url":null,"abstract":"Abstract Current climate models are complex computer programs that are typically iterated time-step by time-step to predict the next set of values of the climate-related variables. Since these iterative methods are necessarily computed only for a fixed number of iterations, they are unable to answer the natural question whether there is a limit to the rise of global temperature. In order to answer that question we propose to combine climate models with software verification techniques that can find invariant conditions for the set of program variables. In particular, we apply the constraint database approach to software verification to find that the rise in global temperature is bounded according to the common Java Climate Model that implements the Wigley/Raper Upwelling-Diffusion Energy Balance Model climate model.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"63 1","pages":"23 - 5"},"PeriodicalIF":0.3,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84148103","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}
Abstract A vertex v of a given graph is said to be in a rainbow neighbourhood of G if every color class of G consists of at least one vertex from the closed neighbourhood N[v]. A maximal proper coloring of a graph G is a J-coloring if and only if every vertex of G belongs to a rainbow neighbourhood of G. In general all graphs need not have a J-coloring, even though they admit a chromatic coloring. In this paper, we characterise graphs which admit a J-coloring. We also discuss some preliminary results in respect of certain graph operations which admit a J-coloring under certain conditions.
{"title":"J-coloring of graph operations","authors":"S. Naduvath, J. Kok","doi":"10.2478/ausi-2019-0007","DOIUrl":"https://doi.org/10.2478/ausi-2019-0007","url":null,"abstract":"Abstract A vertex v of a given graph is said to be in a rainbow neighbourhood of G if every color class of G consists of at least one vertex from the closed neighbourhood N[v]. A maximal proper coloring of a graph G is a J-coloring if and only if every vertex of G belongs to a rainbow neighbourhood of G. In general all graphs need not have a J-coloring, even though they admit a chromatic coloring. In this paper, we characterise graphs which admit a J-coloring. We also discuss some preliminary results in respect of certain graph operations which admit a J-coloring under certain conditions.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"386 1","pages":"108 - 95"},"PeriodicalIF":0.3,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76617069","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}
Abstract To reconstruct the points in three dimensional space, we need at least two images. In this paper we compared two different methods: the first uses only two images, the second one uses three. During the research we measured how camera resolution, camera angles and camera distances influence the number of reconstructed points and the dispersion of them. The paper presents that using the two-view method, we can reconstruct significantly more points than using the other one, but the dispersion of points is smaller if we use the three-view method. Taking into consideration the different camera settings, we can say that both the two- and three-view method behaves the same, and the best parameters are also the same for both methods.
{"title":"Comparing two- and three-view computer vision","authors":"Zsolt Levente Kucsván","doi":"10.2478/ausi-2019-0003","DOIUrl":"https://doi.org/10.2478/ausi-2019-0003","url":null,"abstract":"Abstract To reconstruct the points in three dimensional space, we need at least two images. In this paper we compared two different methods: the first uses only two images, the second one uses three. During the research we measured how camera resolution, camera angles and camera distances influence the number of reconstructed points and the dispersion of them. The paper presents that using the two-view method, we can reconstruct significantly more points than using the other one, but the dispersion of points is smaller if we use the three-view method. Taking into consideration the different camera settings, we can say that both the two- and three-view method behaves the same, and the best parameters are also the same for both methods.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"1 1","pages":"41 - 51"},"PeriodicalIF":0.3,"publicationDate":"2019-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91032958","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}
Abstract A tournament is an orientation of a complete simple graph. The score of a vertex in a tournament is the outdegree of the vertex. In this paper, we obtain various results on the scores in tournaments.
{"title":"On scores in tournaments","authors":"T. A. Naikoo","doi":"10.2478/ausi-2018-0013","DOIUrl":"https://doi.org/10.2478/ausi-2018-0013","url":null,"abstract":"Abstract A tournament is an orientation of a complete simple graph. The score of a vertex in a tournament is the outdegree of the vertex. In this paper, we obtain various results on the scores in tournaments.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"438 1","pages":"257 - 267"},"PeriodicalIF":0.3,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72505857","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}
Abstract The authors in the paper [15] presented an algorithm that generates uniformly all the bipartite realizations and the other algorithm that generates uniformly all the simple bipartite realizations whenever A is a bipartite degree sequence of a simple graph. The running time of both algorithms is 𝒪(m),where m=12∑i=1nai ${rm{m}} = {1 over 2}sumnolimits_{rm {i} = 1}^n {{ rm{a}_rm {i}}}$ . Let A =(A1 : A2 : ... : Ak) be a k-partite degree sequence of a simple graph, where Ai has ni entries such that ∑ni=n. In the present article, we give a generalized algorithm that generates uniformly all the k-partite realizations of A and another algorithm that generates uniformly all the simple k-partite realizations of A. The running time of both algorithms is 𝒪(m), where m=12∑i=1nai $m = {1 over 2}sumnolimits_{i = 1}^n {{a_i}}$ .
{"title":"Sampling k-partite graphs with a given degree sequence","authors":"K. K. Kayibi, U. Samee, S. Pirzada, M. A. Khan","doi":"10.2478/ausi-2018-0010","DOIUrl":"https://doi.org/10.2478/ausi-2018-0010","url":null,"abstract":"Abstract The authors in the paper [15] presented an algorithm that generates uniformly all the bipartite realizations and the other algorithm that generates uniformly all the simple bipartite realizations whenever A is a bipartite degree sequence of a simple graph. The running time of both algorithms is 𝒪(m),where m=12∑i=1nai ${rm{m}} = {1 over 2}sumnolimits_{rm {i} = 1}^n {{ rm{a}_rm {i}}}$ . Let A =(A1 : A2 : ... : Ak) be a k-partite degree sequence of a simple graph, where Ai has ni entries such that ∑ni=n. In the present article, we give a generalized algorithm that generates uniformly all the k-partite realizations of A and another algorithm that generates uniformly all the simple k-partite realizations of A. The running time of both algorithms is 𝒪(m), where m=12∑i=1nai $m = {1 over 2}sumnolimits_{i = 1}^n {{a_i}}$ .","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"27 1","pages":"183 - 217"},"PeriodicalIF":0.3,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81218912","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}
Abstract It is a common practice to find upper bound for clique number via legal coloring of the nodes of the graph. We will point out that with a little extra work we may lower this bound. Applying this procedure to a suitably constructed auxiliary graph one may further improve the clique size estimate of the original graph.
{"title":"Estimating clique size by coloring the nodes of auxiliary graphs","authors":"S. Szabó","doi":"10.2478/ausi-2018-0008","DOIUrl":"https://doi.org/10.2478/ausi-2018-0008","url":null,"abstract":"Abstract It is a common practice to find upper bound for clique number via legal coloring of the nodes of the graph. We will point out that with a little extra work we may lower this bound. Applying this procedure to a suitably constructed auxiliary graph one may further improve the clique size estimate of the original graph.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"53 1","pages":"137 - 157"},"PeriodicalIF":0.3,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80292655","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：