Pub Date : 2017-11-22DOI: 10.1109/INES.2017.8118569
B. Czakó, Johanna Sápi, L. Kovács
Cancerous diseases are being responsible for the death of many around the globe. Treating these illnesses pose a significant challenge to the medical professionals. While conventional methods, chemotherapy or radiotherapy for example, provide a remedy to the issue their side effects are not negligible. In the past few decades new methods have emerged, which could hinder the strength of the side effects and most remarkably, anti-angiogenic therapy can make a notable difference in every day cancer treatment. While the technique has many advantages the cost of treatments are often expensive due to the non-personalized administration medical protocols. In this paper a model based solution is provided which aims to lower the medical expenses during the treatment by creating personalized administration plans with the help of control engineering.
{"title":"Model-based optimal control method for cancer treatment using model predictive control and robust fixed point method","authors":"B. Czakó, Johanna Sápi, L. Kovács","doi":"10.1109/INES.2017.8118569","DOIUrl":"https://doi.org/10.1109/INES.2017.8118569","url":null,"abstract":"Cancerous diseases are being responsible for the death of many around the globe. Treating these illnesses pose a significant challenge to the medical professionals. While conventional methods, chemotherapy or radiotherapy for example, provide a remedy to the issue their side effects are not negligible. In the past few decades new methods have emerged, which could hinder the strength of the side effects and most remarkably, anti-angiogenic therapy can make a notable difference in every day cancer treatment. While the technique has many advantages the cost of treatments are often expensive due to the non-personalized administration medical protocols. In this paper a model based solution is provided which aims to lower the medical expenses during the treatment by creating personalized administration plans with the help of control engineering.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125892446","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 : 2017-11-22DOI: 10.1109/INES.2017.8118567
G. Eigner, Katalin Koppány, Péter Pausits, L. Kovács
In case of biomedical researches we often have to deal with complicated biological phenomenons, which are usually described with complex mathematical models. In most cases these mathematical models and the systems to be modelled are also nonlinear. The appropriate adjustment of the parameters of these models is always a problem which is hard to be solved. To work with such complex models is essential in many research fields and application areas e.g. in personalized medicine or by the control of physiological processes. Although there are many identification techniques available, there is no general or “oven-ready” solution in cases where the mathematical model describing the dynamics of the physiological processes is highly nonlinear. One of our aims was to develop a simple, user-friendly and flexible identification framework which supports the identification of complex, nonlinear mathematical models. The performance of the method can be measured by simple metric. On the other hand, our goal was to successfully realize the identification framework in case of glucose absorption models, which are essential in our future work in order to validate the performance of advanced control algorithms. Our results show that the nonlinear identification framework performed well, since the predefined requirements were satisfied in all cases.
{"title":"Nonlinear identification of glucose absorption related to Diabetes Mellitus","authors":"G. Eigner, Katalin Koppány, Péter Pausits, L. Kovács","doi":"10.1109/INES.2017.8118567","DOIUrl":"https://doi.org/10.1109/INES.2017.8118567","url":null,"abstract":"In case of biomedical researches we often have to deal with complicated biological phenomenons, which are usually described with complex mathematical models. In most cases these mathematical models and the systems to be modelled are also nonlinear. The appropriate adjustment of the parameters of these models is always a problem which is hard to be solved. To work with such complex models is essential in many research fields and application areas e.g. in personalized medicine or by the control of physiological processes. Although there are many identification techniques available, there is no general or “oven-ready” solution in cases where the mathematical model describing the dynamics of the physiological processes is highly nonlinear. One of our aims was to develop a simple, user-friendly and flexible identification framework which supports the identification of complex, nonlinear mathematical models. The performance of the method can be measured by simple metric. On the other hand, our goal was to successfully realize the identification framework in case of glucose absorption models, which are essential in our future work in order to validate the performance of advanced control algorithms. Our results show that the nonlinear identification framework performed well, since the predefined requirements were satisfied in all cases.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126114636","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 : 2017-10-01DOI: 10.1109/INES.2017.8118531
J. Hurtuk, M. Chovanec, N. Ádám
In order to keep up with the massive growing and expanding development of the electronics and informatics fields of study, the education system should be able to react on the currently used technologies available on the market and include them into the education process. Meeting the new trends becomes crucial when producing the people with broad view, experience and insight. Nowadays, Arduino based technologies are gaining huge popularity among the communities interested in fields of electronic and hardware solutions, because of its availability on the market, relatively easy use and last but not least, because of its cheap price and large accessibility of various information, components and already made tutorials. Therefore it becomes more and more crucial to include Arduino into education process within the subjects taught on schools, which would like to provide the complex view of electronics and informatics connected fields of study.
{"title":"The Arduino platform connected to education process","authors":"J. Hurtuk, M. Chovanec, N. Ádám","doi":"10.1109/INES.2017.8118531","DOIUrl":"https://doi.org/10.1109/INES.2017.8118531","url":null,"abstract":"In order to keep up with the massive growing and expanding development of the electronics and informatics fields of study, the education system should be able to react on the currently used technologies available on the market and include them into the education process. Meeting the new trends becomes crucial when producing the people with broad view, experience and insight. Nowadays, Arduino based technologies are gaining huge popularity among the communities interested in fields of electronic and hardware solutions, because of its availability on the market, relatively easy use and last but not least, because of its cheap price and large accessibility of various information, components and already made tutorials. Therefore it becomes more and more crucial to include Arduino into education process within the subjects taught on schools, which would like to provide the complex view of electronics and informatics connected fields of study.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116146881","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 : 2017-10-01DOI: 10.1109/INES.2017.8118557
F. Kobayashi, Shin-ichi Higuchi, Junaidah Bt Zakaria, Mohamad Zain Azreen B Ramli
Though intelligent systems are usually realized by software, some functionality can more efficiently be implemented by hardware. Among hardware fronts, dynamic reconfiguration (DR) and analog are most outstanding. This paper proposes a scheme to coordinate multi-chip circuits to implement intelligence by analog DR.
{"title":"Inter-chip synchronism in dynamically reconfigurable analog circuits for intelligent engineering systems","authors":"F. Kobayashi, Shin-ichi Higuchi, Junaidah Bt Zakaria, Mohamad Zain Azreen B Ramli","doi":"10.1109/INES.2017.8118557","DOIUrl":"https://doi.org/10.1109/INES.2017.8118557","url":null,"abstract":"Though intelligent systems are usually realized by software, some functionality can more efficiently be implemented by hardware. Among hardware fronts, dynamic reconfiguration (DR) and analog are most outstanding. This paper proposes a scheme to coordinate multi-chip circuits to implement intelligence by analog DR.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"226 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115192956","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 : 2017-10-01DOI: 10.1109/ines.2017.8118549
Marie Kiermeier, Sebastian Feld, Claudia Linnhoff-Popien
In self-organizing industrial systems (SOIS) workflows are not defined by engineers in advance, but the system decides by itself at runtime how to route workpieces through the factory, so that the desired output is manufactured as optimal as possible in the present circumstances. As a consequence, the number of possible workflows is not limited to those which were manually predefined, but limited to all possible routes in the factory (state space explosion). Accordingly, analyzing anomalies in such a huge solution space becomes more challenging. In this paper, we present a root cause analyis (RCA) approach for finding the root cause of global anomalous events which handles this state space explosion in SOIS. To do so, the dependencies between path usage and external factors like available machines and demanded tasks are subdivided into several sub-dependencies. In addition, we propose for one of these sub-dependencies a heuristical description which avoids the enormous computational effort for modeling the dependency exactly. The operating principle of our RCA method is evaluated based on simulation data of an example factory.
{"title":"Root cause analysis for global anomalous events in self-organizing industrial systems","authors":"Marie Kiermeier, Sebastian Feld, Claudia Linnhoff-Popien","doi":"10.1109/ines.2017.8118549","DOIUrl":"https://doi.org/10.1109/ines.2017.8118549","url":null,"abstract":"In self-organizing industrial systems (SOIS) workflows are not defined by engineers in advance, but the system decides by itself at runtime how to route workpieces through the factory, so that the desired output is manufactured as optimal as possible in the present circumstances. As a consequence, the number of possible workflows is not limited to those which were manually predefined, but limited to all possible routes in the factory (state space explosion). Accordingly, analyzing anomalies in such a huge solution space becomes more challenging. In this paper, we present a root cause analyis (RCA) approach for finding the root cause of global anomalous events which handles this state space explosion in SOIS. To do so, the dependencies between path usage and external factors like available machines and demanded tasks are subdivided into several sub-dependencies. In addition, we propose for one of these sub-dependencies a heuristical description which avoids the enormous computational effort for modeling the dependency exactly. The operating principle of our RCA method is evaluated based on simulation data of an example factory.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116977201","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 : 2017-10-01DOI: 10.1109/ines.2017.8118566
C. Copot
In this paper, a control strategy based on fractional order approach for visual servoing systems is investigated. The proposed image-based control strategy is a fractional-order PI which takes into account the point features. In order to evaluate the designed control strategy, a visual servoing simulator consisting of a manipulator robot with 6 degrees of freedom (d.o.f.) and an eye-in-hand camera configuration was considered. The validity of the visual based controllers is shown by the simulation results which demonstrate that the proposed approach based on a fractional-order controller has a stable and convergent behavior when dealing with visual servoing applications. Simulations have been performed and the results revealed that the image-based fractional-order PI controller outperforms the conventional image-based integer-order PI controller.
{"title":"Visual servoing of moving targets through fractional control: A feasibility study","authors":"C. Copot","doi":"10.1109/ines.2017.8118566","DOIUrl":"https://doi.org/10.1109/ines.2017.8118566","url":null,"abstract":"In this paper, a control strategy based on fractional order approach for visual servoing systems is investigated. The proposed image-based control strategy is a fractional-order PI which takes into account the point features. In order to evaluate the designed control strategy, a visual servoing simulator consisting of a manipulator robot with 6 degrees of freedom (d.o.f.) and an eye-in-hand camera configuration was considered. The validity of the visual based controllers is shown by the simulation results which demonstrate that the proposed approach based on a fractional-order controller has a stable and convergent behavior when dealing with visual servoing applications. Simulations have been performed and the results revealed that the image-based fractional-order PI controller outperforms the conventional image-based integer-order PI controller.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123913500","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 : 2017-10-01DOI: 10.1109/INES.2017.8118577
David Coufal
A fuzzy system with desirable properties is proposed and investigated. Membership functions used in the system are smooth functions with compact support. A suitable i-norm is designed so that the shape of employed fuzzy sets is preserved after their combination. This is called the radial property. Smoothness and the radial property makes the computational model of the proposed fuzzy system mathematically convenient, especially when data-driven learning capabilities are taken into account.
{"title":"On smooth compactly supportée radial fuzzy system","authors":"David Coufal","doi":"10.1109/INES.2017.8118577","DOIUrl":"https://doi.org/10.1109/INES.2017.8118577","url":null,"abstract":"A fuzzy system with desirable properties is proposed and investigated. Membership functions used in the system are smooth functions with compact support. A suitable i-norm is designed so that the shape of employed fuzzy sets is preserved after their combination. This is called the radial property. Smoothness and the radial property makes the computational model of the proposed fuzzy system mathematically convenient, especially when data-driven learning capabilities are taken into account.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125738051","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 : 2017-10-01DOI: 10.1109/INES.2017.8118561
Georgios L. Giannaris, N. Kouvakas, F. Koumboulis, D. Vouyioukas
The problem of remote position control of a planar redundant manipulator is studied for the case of a 3dof Cartesian robot including disturbance forces at the end effector. The robotic manipulator controlled through a wireless network using the ZigBee protocol, imposing communication delays between the sensors and the controller, as well as between the controller and actuators. The kinetic model of the system is presented and a static feedback with dynamic precompensator controller involving time delays is proposed. Based on these two aspects the following four design goals are imposed: a) non-square I/O decoupling, b) D/O diagonalization, c) attenuation of the influence of the disturbances to the performance output, and d) balanced allotment of the steady state behavior of the redundant degrees of freedom. The design goals are proven to be satisfied and the solution of the controller matrices are derived.
{"title":"Towards remote control of planar redundant robotic manipulators","authors":"Georgios L. Giannaris, N. Kouvakas, F. Koumboulis, D. Vouyioukas","doi":"10.1109/INES.2017.8118561","DOIUrl":"https://doi.org/10.1109/INES.2017.8118561","url":null,"abstract":"The problem of remote position control of a planar redundant manipulator is studied for the case of a 3dof Cartesian robot including disturbance forces at the end effector. The robotic manipulator controlled through a wireless network using the ZigBee protocol, imposing communication delays between the sensors and the controller, as well as between the controller and actuators. The kinetic model of the system is presented and a static feedback with dynamic precompensator controller involving time delays is proposed. Based on these two aspects the following four design goals are imposed: a) non-square I/O decoupling, b) D/O diagonalization, c) attenuation of the influence of the disturbances to the performance output, and d) balanced allotment of the steady state behavior of the redundant degrees of freedom. The design goals are proven to be satisfied and the solution of the controller matrices are derived.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128883773","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 : 2017-10-01DOI: 10.1109/INES.2017.8118534
Sheikh Shanawaz Mostafa, Fábio Mendonça, F. Morgado‐Dias, A. Ravelo-García
In a classical classification process, automatic sleep apnea detection involves creating and selecting the features, using prior knowledge, and apply them to a classifier. A different approach is applied in this paper, where a Deep Belief Network is used for feature extraction, without using domain-specific knowledge, and then the same network is used for classification of sleep apnea. The Deep Belief Network was created by stacking Restricted Boltzmann Machines. The first two layers are autoencoder type and the last layer is of soft-max type. The initial weights are calculated using unsupervised learning and, at the end, a supervised fine-tuning of the weights is performed. Two public databases, one with 8 subjects and other with 25 subjects, are tested using tenfold cross validation. The optimum number of hidden neurons of this problem is found using a search technique. The accuracy achieved from UCD database is 85.26% and Apnea-ECG database is 97.64%.
{"title":"SpO2 based sleep apnea detection using deep learning","authors":"Sheikh Shanawaz Mostafa, Fábio Mendonça, F. Morgado‐Dias, A. Ravelo-García","doi":"10.1109/INES.2017.8118534","DOIUrl":"https://doi.org/10.1109/INES.2017.8118534","url":null,"abstract":"In a classical classification process, automatic sleep apnea detection involves creating and selecting the features, using prior knowledge, and apply them to a classifier. A different approach is applied in this paper, where a Deep Belief Network is used for feature extraction, without using domain-specific knowledge, and then the same network is used for classification of sleep apnea. The Deep Belief Network was created by stacking Restricted Boltzmann Machines. The first two layers are autoencoder type and the last layer is of soft-max type. The initial weights are calculated using unsupervised learning and, at the end, a supervised fine-tuning of the weights is performed. Two public databases, one with 8 subjects and other with 25 subjects, are tested using tenfold cross validation. The optimum number of hidden neurons of this problem is found using a search technique. The accuracy achieved from UCD database is 85.26% and Apnea-ECG database is 97.64%.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132203137","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 : 2017-10-01DOI: 10.1109/INES.2017.8118574
S. Orzen, S. Babii
In this paper the creation of network events and their usefulness is presented for real-time session fault tolerance. Network fault tolerance is a defined event driven action and for real-time sessions the timely processing of events is of the highest importance. Real-time communications have always had a large spectrum of performance criteria that needed to be accomplished and throughout this paper their creation and registration in systems as guideline events is represented. Our research is mostly based on queue based event tuning and this is done in a comprehensive manner that defines when actions happen because of performance flaw occurrences. The application of our defined method for performing fault tolerant actions at a real-time level is presented with the use of a simulation methodology which quantifies unitary and global communication paths.
{"title":"Network events in the dynamic selection of real-time session fault tolerant routes","authors":"S. Orzen, S. Babii","doi":"10.1109/INES.2017.8118574","DOIUrl":"https://doi.org/10.1109/INES.2017.8118574","url":null,"abstract":"In this paper the creation of network events and their usefulness is presented for real-time session fault tolerance. Network fault tolerance is a defined event driven action and for real-time sessions the timely processing of events is of the highest importance. Real-time communications have always had a large spectrum of performance criteria that needed to be accomplished and throughout this paper their creation and registration in systems as guideline events is represented. Our research is mostly based on queue based event tuning and this is done in a comprehensive manner that defines when actions happen because of performance flaw occurrences. The application of our defined method for performing fault tolerant actions at a real-time level is presented with the use of a simulation methodology which quantifies unitary and global communication paths.","PeriodicalId":344933,"journal":{"name":"2017 IEEE 21st International Conference on Intelligent Engineering Systems (INES)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132353534","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：