Pub Date : 2021-11-18DOI: 10.1109/CINTI53070.2021.9668416
P. Galambos
In March of 2020, with the leadership of Obuda University, we established the Cyber-medical Competence Center in cooperation with the Research Center for Natural Sciences and the 3DHISTECH Ltd. The primary mission of this profoundly interdisciplinary organization is to introduce radically new approaches in a wide range of modern medicine through the synergies of engineering and mathematics with modern cell biology, genetics, and other medical sciences. Besides the basic research, the consortium aims to develop market-ready methods, software- and hardware products. With our joint forces, four main topics are addressed: New cancer treatment protocols with individual smart therapy; Supportive technologies for diabetes patients; Tissue analysis through single-cell genome sequencing and digital imaging with advanced visualization; Flexible automation of life science laboratories using robots. In my presentation, I introduce the motivation behind the Cyber-medical Competence Center under the conceptual framework of Cyber-Medical Systems. The lecture will focus on featured topics and research results achieved with the major contribution of the research teams of Obuda University.
{"title":"Control science, AI and Robotics in Cyber Medicine: Featured topics of the Cybermedical Competence Center at Óbuda University","authors":"P. Galambos","doi":"10.1109/CINTI53070.2021.9668416","DOIUrl":"https://doi.org/10.1109/CINTI53070.2021.9668416","url":null,"abstract":"In March of 2020, with the leadership of Obuda University, we established the Cyber-medical Competence Center in cooperation with the Research Center for Natural Sciences and the 3DHISTECH Ltd. The primary mission of this profoundly interdisciplinary organization is to introduce radically new approaches in a wide range of modern medicine through the synergies of engineering and mathematics with modern cell biology, genetics, and other medical sciences. Besides the basic research, the consortium aims to develop market-ready methods, software- and hardware products. With our joint forces, four main topics are addressed: New cancer treatment protocols with individual smart therapy; Supportive technologies for diabetes patients; Tissue analysis through single-cell genome sequencing and digital imaging with advanced visualization; Flexible automation of life science laboratories using robots. In my presentation, I introduce the motivation behind the Cyber-medical Competence Center under the conceptual framework of Cyber-Medical Systems. The lecture will focus on featured topics and research results achieved with the major contribution of the research teams of Obuda University.","PeriodicalId":340545,"journal":{"name":"2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI)","volume":" 19","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132094739","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 : 2021-11-18DOI: 10.1109/CINTI53070.2021.9668604
L. Horváth
Work for this paper was motivated by the recognition that cooperation between engineering model system (EMS) representing cyber physical system (CPS) and cyber units of represented CPS is essential for both sides mainly to assist critical decisions. While EMS provides sophisticated model representations, procedures and much more for CPS, CPS acts as verified source of experience information to enhance models in EMS. This cooperation results theoretically grounded and, at the same time, experience proven representation fulfilling one of the essential current requirements against EMS. This paper contributes to methodology for the above connection mainly to enhance autonomous cooperation between EMS and the related cyber units of CPS. Cooperation between virtual and physical CPS configurations are analyzed using new organized scenario. Results of this analysis are applied at development concept and process to provide autonomous EMS (AEM) support for engineering in autonomous CPS. Following this, concept of model mediated research (MMR) is introduced to support research in engineering for AEM and CPS. Finally, experimental implementation of MMR concept in activity of the Virtual Research Laboratory (VRL) at the Doctoral School of Applied Informatics and Applied Mathematics (AIAMDI), Obuda University is discussed.
{"title":"Contextual Integration of Activities in Virtual and Field Operating Cyber Physical Systems","authors":"L. Horváth","doi":"10.1109/CINTI53070.2021.9668604","DOIUrl":"https://doi.org/10.1109/CINTI53070.2021.9668604","url":null,"abstract":"Work for this paper was motivated by the recognition that cooperation between engineering model system (EMS) representing cyber physical system (CPS) and cyber units of represented CPS is essential for both sides mainly to assist critical decisions. While EMS provides sophisticated model representations, procedures and much more for CPS, CPS acts as verified source of experience information to enhance models in EMS. This cooperation results theoretically grounded and, at the same time, experience proven representation fulfilling one of the essential current requirements against EMS. This paper contributes to methodology for the above connection mainly to enhance autonomous cooperation between EMS and the related cyber units of CPS. Cooperation between virtual and physical CPS configurations are analyzed using new organized scenario. Results of this analysis are applied at development concept and process to provide autonomous EMS (AEM) support for engineering in autonomous CPS. Following this, concept of model mediated research (MMR) is introduced to support research in engineering for AEM and CPS. Finally, experimental implementation of MMR concept in activity of the Virtual Research Laboratory (VRL) at the Doctoral School of Applied Informatics and Applied Mathematics (AIAMDI), Obuda University is discussed.","PeriodicalId":340545,"journal":{"name":"2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133395594","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 : 2021-11-18DOI: 10.1109/CINTI53070.2021.9668492
Miklós Vincze, Kristóf Tamás Papp, Doaa Mahmoud, Abdallah Benhamida, M. Kucarov, Róbert Paulik, V. Jonas, Melvin Ogbolu, M. Kozlovszky
Today, 2D visualization programs became more common in digital pathology. The use of these programs makes it possible to overcome the difficulties that were present in previous microscopic examinations. With these programs, you no longer have to worry about damaging the sample placed on the glass plate and no need to deal with physical samples for security or infection reasons, or perhaps the biggest advantage of such software, that the test is no longer stationary. Virtual reality technology is evolving at an ever-increasing rate and became more and more available for the average person. The purpose of this paper is to demonstrate the structure and operation of a software called PathoVrthat, in addition to the benefits of 2D visualization solutions, also uses virtual reality in a 3D visualization program. The program provides the ability to load two-dimensional digitized serial sections in virtual reality and is able to visualize various laboratory results on the samples displayed in virtual reality. We used the so-called Godot game engine when developing the software.
{"title":"Displaying Digitalized Pathological Tissue Samples In 3D Using Virtual Reality","authors":"Miklós Vincze, Kristóf Tamás Papp, Doaa Mahmoud, Abdallah Benhamida, M. Kucarov, Róbert Paulik, V. Jonas, Melvin Ogbolu, M. Kozlovszky","doi":"10.1109/CINTI53070.2021.9668492","DOIUrl":"https://doi.org/10.1109/CINTI53070.2021.9668492","url":null,"abstract":"Today, 2D visualization programs became more common in digital pathology. The use of these programs makes it possible to overcome the difficulties that were present in previous microscopic examinations. With these programs, you no longer have to worry about damaging the sample placed on the glass plate and no need to deal with physical samples for security or infection reasons, or perhaps the biggest advantage of such software, that the test is no longer stationary. Virtual reality technology is evolving at an ever-increasing rate and became more and more available for the average person. The purpose of this paper is to demonstrate the structure and operation of a software called PathoVrthat, in addition to the benefits of 2D visualization solutions, also uses virtual reality in a 3D visualization program. The program provides the ability to load two-dimensional digitized serial sections in virtual reality and is able to visualize various laboratory results on the samples displayed in virtual reality. We used the so-called Godot game engine when developing the software.","PeriodicalId":340545,"journal":{"name":"2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117183868","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 : 2021-11-18DOI: 10.1109/CINTI53070.2021.9668384
Fruzsina Kulcsár, Dániel Békevári, G. Eigner, D. Drexler, Á. Patai, T. Micsik, Rita Fleiner
The 4 Consensus Molecular Subtypes (CMS1-4) determined by the Colorectal Cancer subtyping Consortium (CRCSC) could have been identified by high-priced methods so far. This study aimed at building a model which can reliably classify patients into the same subtypes with high accuracy using data from publicly available datasets and less expensive clinical procedures. The gene expression data from The Cancer Genome Atlas (TCGA) database was used as a basis for classifying the patients. Our objective was to decrease the number of considered genes from 20000 to around 100 without significant deterioration of the predictive ability of the model. In order to perform the classification, Artificial Neural Networks were trained for the labeled data of the total number of dimensions checking the goodness of the patient classification. Then dimensionality reduction was used, paying attention not to decrease the integrity of the classification significantly. We managed to reduce the number of genes to 100, while we did not deteriorate the accuracy of the classification drastically. The final model on the reduced geneset produced a result of 82% accuracy. The developed software can be used for classifying patients with colorectal cancer. The 100 genes have to be provided for each patient, and the software returns 4 probabilities as a result: the probabilities of belonging to either of the 4 subtypes. The subtype with the highest probability is the final result of the classification.
迄今为止，结直肠癌亚型联盟(CRCSC)确定的4种共识分子亚型(CMS1-4)可以通过高价方法进行鉴定。本研究旨在建立一个模型，该模型可以使用来自公开数据集的数据和更便宜的临床程序，以高精度可靠地将患者分为相同的亚型。肿瘤基因组图谱(The Cancer Genome Atlas, TCGA)数据库中的基因表达数据作为患者分类的依据。我们的目标是将考虑的基因数量从20000个减少到100个左右，同时不显著降低模型的预测能力。为了进行分类，对总维数的标记数据进行人工神经网络训练，检验患者分类的优良性。然后采用降维方法，注意不显著降低分类的完整性。我们设法将基因数量减少到100个，而我们并没有大幅降低分类的准确性。在简化的基因集上的最终模型产生了82%的准确率。所开发的软件可用于结直肠癌患者的分类。必须为每个患者提供100个基因，然后软件返回4种概率:属于4种亚型中的任何一种的概率。概率最高的子类型是分类的最终结果。
{"title":"Development of Machine Learning based Colorectal Cancer Subtype Classificator*","authors":"Fruzsina Kulcsár, Dániel Békevári, G. Eigner, D. Drexler, Á. Patai, T. Micsik, Rita Fleiner","doi":"10.1109/CINTI53070.2021.9668384","DOIUrl":"https://doi.org/10.1109/CINTI53070.2021.9668384","url":null,"abstract":"The 4 Consensus Molecular Subtypes (CMS1-4) determined by the Colorectal Cancer subtyping Consortium (CRCSC) could have been identified by high-priced methods so far. This study aimed at building a model which can reliably classify patients into the same subtypes with high accuracy using data from publicly available datasets and less expensive clinical procedures. The gene expression data from The Cancer Genome Atlas (TCGA) database was used as a basis for classifying the patients. Our objective was to decrease the number of considered genes from 20000 to around 100 without significant deterioration of the predictive ability of the model. In order to perform the classification, Artificial Neural Networks were trained for the labeled data of the total number of dimensions checking the goodness of the patient classification. Then dimensionality reduction was used, paying attention not to decrease the integrity of the classification significantly. We managed to reduce the number of genes to 100, while we did not deteriorate the accuracy of the classification drastically. The final model on the reduced geneset produced a result of 82% accuracy. The developed software can be used for classifying patients with colorectal cancer. The 100 genes have to be provided for each patient, and the software returns 4 probabilities as a result: the probabilities of belonging to either of the 4 subtypes. The subtype with the highest probability is the final result of the classification.","PeriodicalId":340545,"journal":{"name":"2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132113519","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 : 2021-11-18DOI: 10.1109/CINTI53070.2021.9668348
Doaa Mahmoud, András Bálint Tóth, E. Kail, Anna Bánáti
5G is not only a new generation of mobile communication generations, but it is a revolutionary technology that supports previous applications and enables new ones because of its great benefits such as high data rate, low latency, massive connectivity, and network reliability. However, the huge number of connected devices, the enablers technologies, reliance on virtualization and cloud services will lead to many new threats besides the old threats and attacks. Consequently, there is a serious need to find out these threats and check appropriate countermeasures, that ensure a robust and secure communication system. In this paper, we provide a brief review of 5G architecture and related security vulnerabilities that can be monitored and detected in a Security Operation Center.
{"title":"5G Vulnarabilities from Security Operation Center's Perspective","authors":"Doaa Mahmoud, András Bálint Tóth, E. Kail, Anna Bánáti","doi":"10.1109/CINTI53070.2021.9668348","DOIUrl":"https://doi.org/10.1109/CINTI53070.2021.9668348","url":null,"abstract":"5G is not only a new generation of mobile communication generations, but it is a revolutionary technology that supports previous applications and enables new ones because of its great benefits such as high data rate, low latency, massive connectivity, and network reliability. However, the huge number of connected devices, the enablers technologies, reliance on virtualization and cloud services will lead to many new threats besides the old threats and attacks. Consequently, there is a serious need to find out these threats and check appropriate countermeasures, that ensure a robust and secure communication system. In this paper, we provide a brief review of 5G architecture and related security vulnerabilities that can be monitored and detected in a Security Operation Center.","PeriodicalId":340545,"journal":{"name":"2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126408699","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 : 2021-11-18DOI: 10.1109/CINTI53070.2021.9668608
R. Falque, Teresa Vidal-Calleja, M. McPhee, E. Toohey, A. Alempijevic
Robotics and automation are rapidly becoming part of meat processing operations. Current automation of breaking down a carcass into primals relies on guidance from X-ray, inter-connected with robotised band-saws. While yielding very accurate cutting lines, the use of vision systems for guidance would be significantly more affordable. This work proposes a novel method that solves the annotation transfer between a 3D noise-free cut-ting line annotated on a CT acquired canonical model and a noisy target in the form of a point cloud acquired by RGB-D cameras. The proposed coarse-to-fine method initially aligns the posture of each body using a non-rigid deformation algorithm and then performs a local search to solve the surface correspondence which is later used to morph the template non-rigidly. We quantitatively assess the approach by benchmarking with multiple state-of-the-art algorithms on a public available human pose dataset. We also present a proof of concept evaluation on lamb carcasses.
{"title":"VirtualButcher: Coarse-to-fine Annotation Transfer of Cutting Lines on Noisy Point Cloud Reconstruction","authors":"R. Falque, Teresa Vidal-Calleja, M. McPhee, E. Toohey, A. Alempijevic","doi":"10.1109/CINTI53070.2021.9668608","DOIUrl":"https://doi.org/10.1109/CINTI53070.2021.9668608","url":null,"abstract":"Robotics and automation are rapidly becoming part of meat processing operations. Current automation of breaking down a carcass into primals relies on guidance from X-ray, inter-connected with robotised band-saws. While yielding very accurate cutting lines, the use of vision systems for guidance would be significantly more affordable. This work proposes a novel method that solves the annotation transfer between a 3D noise-free cut-ting line annotated on a CT acquired canonical model and a noisy target in the form of a point cloud acquired by RGB-D cameras. The proposed coarse-to-fine method initially aligns the posture of each body using a non-rigid deformation algorithm and then performs a local search to solve the surface correspondence which is later used to morph the template non-rigidly. We quantitatively assess the approach by benchmarking with multiple state-of-the-art algorithms on a public available human pose dataset. We also present a proof of concept evaluation on lamb carcasses.","PeriodicalId":340545,"journal":{"name":"2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125726875","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：