Pub Date : 2018-05-09DOI: 10.1109/IIPHDW.2018.8388238
M. Raczyński
Speech processing algorithms have been intensive developed since 70's and today are often implemented in daily-use devices (personal computers, mobile phones, smartphones etc.). Unfortunately, advanced algorithms have relatively high calculation costs thus need efficient (and expensive) implementation hardware. In this paper a simple speech-processing algorithm able to recognize a spoken word from previously created constant words set has been presented. This functionality is useful in many applications e.g. in voice controlled switching devices. The described algorithm has relatively low cost with sufficient efficiency and could be implemented in a simple and cheap hardware platform. The basic idea is based on the signal analysis in time domain, where the envelope of the signal is calculated and compared with previous created pattern stored in memory. The algorithm of pattern set creation is based on piecewise linear approximation. Moreover, user could create a collection of words which have to be recognized. The proposed algorithm was written in MATLAB software and tested ‘offline’ on recorded wave files and ‘online’ with music card. Next step of the research will be the implementation of the algorithm in the low-cost 32-bit ARM core microcontroller. Details of used algorithms, first tests, occurred problems and finally conclusions are presented in the paper.
{"title":"Speech processing algorithm for isolated words recognition","authors":"M. Raczyński","doi":"10.1109/IIPHDW.2018.8388238","DOIUrl":"https://doi.org/10.1109/IIPHDW.2018.8388238","url":null,"abstract":"Speech processing algorithms have been intensive developed since 70's and today are often implemented in daily-use devices (personal computers, mobile phones, smartphones etc.). Unfortunately, advanced algorithms have relatively high calculation costs thus need efficient (and expensive) implementation hardware. In this paper a simple speech-processing algorithm able to recognize a spoken word from previously created constant words set has been presented. This functionality is useful in many applications e.g. in voice controlled switching devices. The described algorithm has relatively low cost with sufficient efficiency and could be implemented in a simple and cheap hardware platform. The basic idea is based on the signal analysis in time domain, where the envelope of the signal is calculated and compared with previous created pattern stored in memory. The algorithm of pattern set creation is based on piecewise linear approximation. Moreover, user could create a collection of words which have to be recognized. The proposed algorithm was written in MATLAB software and tested ‘offline’ on recorded wave files and ‘online’ with music card. Next step of the research will be the implementation of the algorithm in the low-cost 32-bit ARM core microcontroller. Details of used algorithms, first tests, occurred problems and finally conclusions are presented in the paper.","PeriodicalId":405270,"journal":{"name":"2018 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"33 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121006634","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 : 2018-05-09DOI: 10.1109/IIPHDW.2018.8388335
E. Piotrowska
This paper deals with the analysis of the electrical circuit with the fractional capacitor as well as the coils described by the fractional order state space equations in the transient state. There are two types of definitions of fractional derivative used in the fractional state space equations which are general solutions. These are the Conformable Fractional Derivative and the Caputo fractional order which are the given cases in different fractional orders. The results show the different voltage's across the super capacitor and current in the coil. The solutions where obtained by using CFD and Caputo definitions using the numerical method.
{"title":"Analysis of fractional capacitor and coil by the use of the Conformable Fractional Derivative and Caputo definitions","authors":"E. Piotrowska","doi":"10.1109/IIPHDW.2018.8388335","DOIUrl":"https://doi.org/10.1109/IIPHDW.2018.8388335","url":null,"abstract":"This paper deals with the analysis of the electrical circuit with the fractional capacitor as well as the coils described by the fractional order state space equations in the transient state. There are two types of definitions of fractional derivative used in the fractional state space equations which are general solutions. These are the Conformable Fractional Derivative and the Caputo fractional order which are the given cases in different fractional orders. The results show the different voltage's across the super capacitor and current in the coil. The solutions where obtained by using CFD and Caputo definitions using the numerical method.","PeriodicalId":405270,"journal":{"name":"2018 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122173696","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 : 2018-05-09DOI: 10.1109/IIPHDW.2018.8388337
Arkadiusz Kwasigroch, Bartlomiej Jarzembinski, M. Grochowski
The diabetic retinopathy is a disease caused by long-standing diabetes. Lack of effective treatment can lead to vision impairment and even irreversible blindness. The disease can be diagnosed by examining digital color fundus photographs of retina. In this paper we propose deep learning approach to automated diabetic retinopathy screening. Deep convolutional neural networks (CNN) — the most popular kind of deep learning algorithms — enjoyed great success in the field of image analysis and recognition. Therefore, we leverage CNN networks to diagnose the diabetic retinopathy and its current stage, based on analysis of the photographs of retina. The utilized models were trained using dataset containing over 88000 retina photographs, labeled by specialist clinicians. To enhance the performance of the system, we proposed a special class coding technique that enabled to include the information about value of difference between predicted score and target score into the objective function being minimized during the neural networks training. To evaluate classification ability of employed models we used standard accuracy metrics and quadratic weighted Kappa score that is calculated between the predicted scores and scores provided in the dataset. The best tested model achieved an accuracy of about 82% in detecting the retinopathy and 51% in assessing its stage. Moreover, system obtained decent Kappa score equal 0.776. Achieved results showed that deep learning algorithms can be successfully employed to solve this very hard to analyze problem.
{"title":"Deep CNN based decision support system for detection and assessing the stage of diabetic retinopathy","authors":"Arkadiusz Kwasigroch, Bartlomiej Jarzembinski, M. Grochowski","doi":"10.1109/IIPHDW.2018.8388337","DOIUrl":"https://doi.org/10.1109/IIPHDW.2018.8388337","url":null,"abstract":"The diabetic retinopathy is a disease caused by long-standing diabetes. Lack of effective treatment can lead to vision impairment and even irreversible blindness. The disease can be diagnosed by examining digital color fundus photographs of retina. In this paper we propose deep learning approach to automated diabetic retinopathy screening. Deep convolutional neural networks (CNN) — the most popular kind of deep learning algorithms — enjoyed great success in the field of image analysis and recognition. Therefore, we leverage CNN networks to diagnose the diabetic retinopathy and its current stage, based on analysis of the photographs of retina. The utilized models were trained using dataset containing over 88000 retina photographs, labeled by specialist clinicians. To enhance the performance of the system, we proposed a special class coding technique that enabled to include the information about value of difference between predicted score and target score into the objective function being minimized during the neural networks training. To evaluate classification ability of employed models we used standard accuracy metrics and quadratic weighted Kappa score that is calculated between the predicted scores and scores provided in the dataset. The best tested model achieved an accuracy of about 82% in detecting the retinopathy and 51% in assessing its stage. Moreover, system obtained decent Kappa score equal 0.776. Achieved results showed that deep learning algorithms can be successfully employed to solve this very hard to analyze problem.","PeriodicalId":405270,"journal":{"name":"2018 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117017060","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 : 2018-05-09DOI: 10.1109/IIPHDW.2018.8388324
P. Kowalski, M. Czyzak
The automatic distance measurement from the high voltage line based on pattern recognition can be used for inspection of high voltage lines. The precise determination of the line position with respect to the measuring device allows to steer the device using the position data. The application example can be the autonomic flight of the flying apparatus along the line with preserving the constant distance from the line. Positioning and trajectory determination can be performed using the digital picture and the line visible in it. The position information can also serve to point other measuring devices. The paper presents a method of the automatic position determination with respect to the measuring device. The measurement uses the stereoscopic picture. The method has been divided into three parts. The first part contains the fast algorithm of the edge detection with the variable sensitivity. It is characterized by the maximum sensitivity to horizontal edges and no vertical sensitivity. The algorithm allows to reduce considerably the data contained in the picture. Thus it is possible to apply more time-consuming algorithms in subsequent processing steps. In the second part the wire detection and numerical shape approximation are performed. In the third part of the method the detected wire shape is used for stereoscopic distance measurement from the high voltage line. The performed experiment have shown the high effectiveness of the method.
{"title":"High voltage line distance measurement and position detection based on stereoscopic image","authors":"P. Kowalski, M. Czyzak","doi":"10.1109/IIPHDW.2018.8388324","DOIUrl":"https://doi.org/10.1109/IIPHDW.2018.8388324","url":null,"abstract":"The automatic distance measurement from the high voltage line based on pattern recognition can be used for inspection of high voltage lines. The precise determination of the line position with respect to the measuring device allows to steer the device using the position data. The application example can be the autonomic flight of the flying apparatus along the line with preserving the constant distance from the line. Positioning and trajectory determination can be performed using the digital picture and the line visible in it. The position information can also serve to point other measuring devices. The paper presents a method of the automatic position determination with respect to the measuring device. The measurement uses the stereoscopic picture. The method has been divided into three parts. The first part contains the fast algorithm of the edge detection with the variable sensitivity. It is characterized by the maximum sensitivity to horizontal edges and no vertical sensitivity. The algorithm allows to reduce considerably the data contained in the picture. Thus it is possible to apply more time-consuming algorithms in subsequent processing steps. In the second part the wire detection and numerical shape approximation are performed. In the third part of the method the detected wire shape is used for stereoscopic distance measurement from the high voltage line. The performed experiment have shown the high effectiveness of the method.","PeriodicalId":405270,"journal":{"name":"2018 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124740766","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 : 2018-05-09DOI: 10.1109/IIPHDW.2018.8388386
J. Grochowalski, T. Chady
The aim of this paper is to present the numerical simulations of a novel eddy current transducer designated for inspection of planar conducting specimens. The transducer consists of the rotating head with permanent magnets which is used to induce the eddy currents in the tested material. The Hall effect device is used to measure changes of a magnetic field caused by the eddy current reaction. Numerical simulations, utilizing a finite element method (FEM) and the COMSOL application, of the transducer is presented in case of an aluminum specimen with different defects.
{"title":"Numerical analysis of eddy current transducer with rotating permanent magnets for planar conducting plates testing","authors":"J. Grochowalski, T. Chady","doi":"10.1109/IIPHDW.2018.8388386","DOIUrl":"https://doi.org/10.1109/IIPHDW.2018.8388386","url":null,"abstract":"The aim of this paper is to present the numerical simulations of a novel eddy current transducer designated for inspection of planar conducting specimens. The transducer consists of the rotating head with permanent magnets which is used to induce the eddy currents in the tested material. The Hall effect device is used to measure changes of a magnetic field caused by the eddy current reaction. Numerical simulations, utilizing a finite element method (FEM) and the COMSOL application, of the transducer is presented in case of an aluminum specimen with different defects.","PeriodicalId":405270,"journal":{"name":"2018 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127867505","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 : 2018-05-09DOI: 10.1109/IIPHDW.2018.8388235
Adam Trojnar, P. Ostalczyk
This paper is concerned with the implementation of a fuel gas valve PID controller in the virtual environment. Dynamic systems simulation software environments provide the opportunity to create and test the entire model instantly and analyze the results. The object of regulation is the position of the gas valve needle fixed on the electromagnet core. The device controls the actuator to minimize error over time by adjustment of a control variable such as the position of the needle to a new location, thereby regulating chamber temperature. The simulation is further compared with real device measurements.
{"title":"Simulation of the fuel gas valve PID controller in closed loop system","authors":"Adam Trojnar, P. Ostalczyk","doi":"10.1109/IIPHDW.2018.8388235","DOIUrl":"https://doi.org/10.1109/IIPHDW.2018.8388235","url":null,"abstract":"This paper is concerned with the implementation of a fuel gas valve PID controller in the virtual environment. Dynamic systems simulation software environments provide the opportunity to create and test the entire model instantly and analyze the results. The object of regulation is the position of the gas valve needle fixed on the electromagnet core. The device controls the actuator to minimize error over time by adjustment of a control variable such as the position of the needle to a new location, thereby regulating chamber temperature. The simulation is further compared with real device measurements.","PeriodicalId":405270,"journal":{"name":"2018 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129066304","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 : 2018-05-09DOI: 10.1109/IIPHDW.2018.8388344
Dawid Bak, P. Mazurek
Air-gap data is important for the security of computer systems. The injection of the computer virus is limited but possible, however data communication channel is necessary for the transmission of stolen data. This paper considers BFSK digital modulation applied to brightness changes of screen for unidirectional transmission of valuable data. Experimental validation and limitations of the proposed technique are provided.
{"title":"Air-gap data transmission using screen brightness modulation","authors":"Dawid Bak, P. Mazurek","doi":"10.1109/IIPHDW.2018.8388344","DOIUrl":"https://doi.org/10.1109/IIPHDW.2018.8388344","url":null,"abstract":"Air-gap data is important for the security of computer systems. The injection of the computer virus is limited but possible, however data communication channel is necessary for the transmission of stolen data. This paper considers BFSK digital modulation applied to brightness changes of screen for unidirectional transmission of valuable data. Experimental validation and limitations of the proposed technique are provided.","PeriodicalId":405270,"journal":{"name":"2018 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116895902","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 : 2018-05-09DOI: 10.1109/IIPHDW.2018.8388338
Agnieszka Mikołajczyk, M. Grochowski
These days deep learning is the fastest-growing field in the field of Machine Learning (ML) and Deep Neural Networks (DNN). Among many of DNN structures, the Convolutional Neural Networks (CNN) are currently the main tool used for the image analysis and classification purposes. Although great achievements and perspectives, deep neural networks and accompanying learning algorithms have some relevant challenges to tackle. In this paper, we have focused on the most frequently mentioned problem in the field of machine learning, that is the lack of sufficient amount of the training data or uneven class balance within the datasets. One of the ways of dealing with this problem is so called data augmentation. In the paper we have compared and analyzed multiple methods of data augmentation in the task of image classification, starting from classical image transformations like rotating, cropping, zooming, histogram based methods and finishing at Style Transfer and Generative Adversarial Networks, along with the representative examples. Next, we presented our own method of data augmentation based on image style transfer. The method allows to generate the new images of high perceptual quality that combine the content of a base image with the appearance of another ones. The newly created images can be used to pre-train the given neural network in order to improve the training process efficiency. Proposed method is validated on the three medical case studies: skin melanomas diagnosis, histopathological images and breast magnetic resonance imaging (MRI) scans analysis, utilizing the image classification in order to provide a diagnose. In such kind of problems the data deficiency is one of the most relevant issues. Finally, we discuss the advantages and disadvantages of the methods being analyzed.
{"title":"Data augmentation for improving deep learning in image classification problem","authors":"Agnieszka Mikołajczyk, M. Grochowski","doi":"10.1109/IIPHDW.2018.8388338","DOIUrl":"https://doi.org/10.1109/IIPHDW.2018.8388338","url":null,"abstract":"These days deep learning is the fastest-growing field in the field of Machine Learning (ML) and Deep Neural Networks (DNN). Among many of DNN structures, the Convolutional Neural Networks (CNN) are currently the main tool used for the image analysis and classification purposes. Although great achievements and perspectives, deep neural networks and accompanying learning algorithms have some relevant challenges to tackle. In this paper, we have focused on the most frequently mentioned problem in the field of machine learning, that is the lack of sufficient amount of the training data or uneven class balance within the datasets. One of the ways of dealing with this problem is so called data augmentation. In the paper we have compared and analyzed multiple methods of data augmentation in the task of image classification, starting from classical image transformations like rotating, cropping, zooming, histogram based methods and finishing at Style Transfer and Generative Adversarial Networks, along with the representative examples. Next, we presented our own method of data augmentation based on image style transfer. The method allows to generate the new images of high perceptual quality that combine the content of a base image with the appearance of another ones. The newly created images can be used to pre-train the given neural network in order to improve the training process efficiency. Proposed method is validated on the three medical case studies: skin melanomas diagnosis, histopathological images and breast magnetic resonance imaging (MRI) scans analysis, utilizing the image classification in order to provide a diagnose. In such kind of problems the data deficiency is one of the most relevant issues. Finally, we discuss the advantages and disadvantages of the methods being analyzed.","PeriodicalId":405270,"journal":{"name":"2018 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122919059","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 : 2018-05-09DOI: 10.1109/IIPHDW.2018.8388328
K. Trela, K. Gawrylczyk
The aim of the article is to present the method of modeling the inductances of the transformer windings, taking into account the complex magnetic permeability of the core material, and verification of obtained results. The research was carried out in two stages. In the first stage, the coil was wound on the distribution transformer core and the inductance of this coil was measured with precision LCR meter in the frequency range of 100Hz–1MHz. Subsequently, the computer model based on 3D Finite Elements Method (FEM) was prepared, while maintaining the original dimensions. The frequency response of the coil has been computed using the energy of the electromagnetic field delivered by FEM. The core model took into account its magnetic loss tangent, electric conductivity and magnetic permeability. Above parameters were parameterized in order to observe their effect on winding frequency response. Finally, the actual coil inductance measurements were compared to the results of computer analysis in order to confront the results of the winding frequency response with the response of computer model. Comparison shows deciding influence of core parameters on the frequency response below the frequency of 100kHz. As a result of the conducted research, a method of modeling the transformer core was proposed, which will be used for calculations the frequency response of the power transformer windings in a wide frequency range.
{"title":"Frequency response modeling of power transformer windings considering the attributes of ferromagnetic core","authors":"K. Trela, K. Gawrylczyk","doi":"10.1109/IIPHDW.2018.8388328","DOIUrl":"https://doi.org/10.1109/IIPHDW.2018.8388328","url":null,"abstract":"The aim of the article is to present the method of modeling the inductances of the transformer windings, taking into account the complex magnetic permeability of the core material, and verification of obtained results. The research was carried out in two stages. In the first stage, the coil was wound on the distribution transformer core and the inductance of this coil was measured with precision LCR meter in the frequency range of 100Hz–1MHz. Subsequently, the computer model based on 3D Finite Elements Method (FEM) was prepared, while maintaining the original dimensions. The frequency response of the coil has been computed using the energy of the electromagnetic field delivered by FEM. The core model took into account its magnetic loss tangent, electric conductivity and magnetic permeability. Above parameters were parameterized in order to observe their effect on winding frequency response. Finally, the actual coil inductance measurements were compared to the results of computer analysis in order to confront the results of the winding frequency response with the response of computer model. Comparison shows deciding influence of core parameters on the frequency response below the frequency of 100kHz. As a result of the conducted research, a method of modeling the transformer core was proposed, which will be used for calculations the frequency response of the power transformer windings in a wide frequency range.","PeriodicalId":405270,"journal":{"name":"2018 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114437695","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 : 2018-05-09DOI: 10.1109/IIPHDW.2018.8388331
Michał Kubicki, Daniel Figurowski
The following article describes a novel implementation of a crossover operator for real-value encoded Genetic Algorithms (GA). The method, Gaussian Crossover Operator (GCO), utilizes the properties of Gaussian functions and Gaussian distribution for offspring generation. Each parent's fitness is evaluated in the context of general population by a heuristic function, i.e. the devised operator is performance based — the parents' individual fitness values act as a basis for a non-deterministic weighing mechanism. The child's gene value is a Gaussian Variable drawn upon the normal distribution determined by the overall state of the algorithm and the antecedent's evaluation. The performance of the algorithm is discussed and compared with the underlaying classical Genetic Algorithm and other GA implementations found in the literature; several test cases are considered. The results show that the proposed Gaussian Crossover Operator is feasible for solving optimization problems.
{"title":"An introduction to a novel crossover operator for real-value encoded genetic algorithm: Gaussian crossover operator","authors":"Michał Kubicki, Daniel Figurowski","doi":"10.1109/IIPHDW.2018.8388331","DOIUrl":"https://doi.org/10.1109/IIPHDW.2018.8388331","url":null,"abstract":"The following article describes a novel implementation of a crossover operator for real-value encoded Genetic Algorithms (GA). The method, Gaussian Crossover Operator (GCO), utilizes the properties of Gaussian functions and Gaussian distribution for offspring generation. Each parent's fitness is evaluated in the context of general population by a heuristic function, i.e. the devised operator is performance based — the parents' individual fitness values act as a basis for a non-deterministic weighing mechanism. The child's gene value is a Gaussian Variable drawn upon the normal distribution determined by the overall state of the algorithm and the antecedent's evaluation. The performance of the algorithm is discussed and compared with the underlaying classical Genetic Algorithm and other GA implementations found in the literature; several test cases are considered. The results show that the proposed Gaussian Crossover Operator is feasible for solving optimization problems.","PeriodicalId":405270,"journal":{"name":"2018 International Interdisciplinary PhD Workshop (IIPhDW)","volume":"40 9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129670547","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：