PROCEEDINGS OF THE INTERNATIONAL CONFERENCE OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2019 (ICCMSE-2019)最新文献

{"title":"Prediction of non-metallic inclusions in steel wires for tire reinforcement by means of machine learning algorithms","authors":"M. Cuartas, E. Ruiz, D. Ferreño, J. Setién, V. Arroyo, F. Gutiérrez-Solana","doi":"10.1063/1.5138082","DOIUrl":"https://doi.org/10.1063/1.5138082","url":null,"abstract":"This study was aimed at developing a reliable Machine Learning algorithm to classify castings of steel for tire reinforcement depending on the number and properties of inclusions, experimentally determined. 855 castings were available for training, validation and testing. 140 parameters are monitored during fabrication, which are the features of the analysis; the output is 1 or 0 depending on whether the casting is rejected or not. The following algorithms have been employed: Logistic Regression, K-Nearest Neighbors, Support Vector Classifier, Random Forests, AdaBoost, Gradient Boosting and Artificial Neural Networks. The reduced value of the rejection rate implies that classification must be carried out on an imbalanced dataset. Resampling methods and specific scores for imbalanced datasets (Recall, Precision and AUC rather than Accuracy) were used. Random Forest was the most successful method providing an area under the curve in the test set of 0.85. No significant improvements were detected after resampling. It has been proved that this tool allows the samples with a higher probability of being rejected to be selected, improving the effectiveness of the quality control. In addition, the optimized Random Forest has enabled to identify the most important features, which have been satisfactorily interpreted on a metallurgical basis.This study was aimed at developing a reliable Machine Learning algorithm to classify castings of steel for tire reinforcement depending on the number and properties of inclusions, experimentally determined. 855 castings were available for training, validation and testing. 140 parameters are monitored during fabrication, which are the features of the analysis; the output is 1 or 0 depending on whether the casting is rejected or not. The following algorithms have been employed: Logistic Regression, K-Nearest Neighbors, Support Vector Classifier, Random Forests, AdaBoost, Gradient Boosting and Artificial Neural Networks. The reduced value of the rejection rate implies that classification must be carried out on an imbalanced dataset. Resampling methods and specific scores for imbalanced datasets (Recall, Precision and AUC rather than Accuracy) were used. Random Forest was the most successful method providing an area under the curve in the test set of 0.85. No significant improvements were detected after resam...","PeriodicalId":20565,"journal":{"name":"PROCEEDINGS OF THE INTERNATIONAL CONFERENCE OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2019 (ICCMSE-2019)","volume":"279 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76327329","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}

{"title":"Numerical evaluation of an internally cracked autofrettaged spherical pressure vessel","authors":"M. Perl, M. Steiner","doi":"10.1063/1.5138080","DOIUrl":"https://doi.org/10.1063/1.5138080","url":null,"abstract":"Internally cracked, fully or partially autofrettaged, spherical pressure vessels are analyzed by numerically calculating 3-D Stress Intensity Factor (SIF) distributions along the fronts of radial lunular or crescentic cracks emanating from the vessel’s bore. The finite element (FE) method is used employing singular elements along the crack front. A novel realistic autofrettage residual stress field incorporating the Bauschinger effect is embodied in the FE model using an equivalent temperature field. The SIFs are extracted by using both the J-integral and the displacement extrapolation methods, and are calculated for three vessel geometries, a wide range of crack depth to wall thickness ratios, various ellipticities, and three levels of autofrettage. A detailed study of the influence of the above parameters on the prevailing SIF is conducted. The results attest to the favorable effect of autofrettage in reducing the SIF, delaying crack initiation, slowing down crack growth rate, and thus, substantially prolonging the fatigue life of the vessel. They also emphasize the importance of properly accounting for the Bauschinger effect including re-yielding, and highlight the significance of the 3-D analysis.Internally cracked, fully or partially autofrettaged, spherical pressure vessels are analyzed by numerically calculating 3-D Stress Intensity Factor (SIF) distributions along the fronts of radial lunular or crescentic cracks emanating from the vessel’s bore. The finite element (FE) method is used employing singular elements along the crack front. A novel realistic autofrettage residual stress field incorporating the Bauschinger effect is embodied in the FE model using an equivalent temperature field. The SIFs are extracted by using both the J-integral and the displacement extrapolation methods, and are calculated for three vessel geometries, a wide range of crack depth to wall thickness ratios, various ellipticities, and three levels of autofrettage. A detailed study of the influence of the above parameters on the prevailing SIF is conducted. The results attest to the favorable effect of autofrettage in reducing the SIF, delaying crack initiation, slowing down crack growth rate, and thus, substantially pr...","PeriodicalId":20565,"journal":{"name":"PROCEEDINGS OF THE INTERNATIONAL CONFERENCE OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2019 (ICCMSE-2019)","volume":"7 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85686073","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}

{"title":"Comparison of hand arches in athletes","authors":"I. Špringrová, Monika Ballýová, Šárka Tomková, E. Bendíková","doi":"10.1063/1.5137994","DOIUrl":"https://doi.org/10.1063/1.5137994","url":null,"abstract":"Aim: Finding out the state of hand arches in press-up positions in a selected sample of participants in relation to their sporting activities. Method: 29 participants took part in the study. The group of athletes consisted of 14 participantsi.e. 12 men and 2 women, age 27 ± 4.4, BMI 22 ± 2kg, frequency of training: 5 ± 1 per week. The control group included 15 participants from the general population, i.e. 8 men and 7 women age 23 ± 2.3, BMI 21.9 ± 2.2 working out no more than once a week without ambition to become professional athletes. The data was analysed in Microsoft Excel 2016 and in Control Freak programme (developed by Contchart Software company), particularly assessment by Shapiro -Wilk test. Results: The average value measured at PodoCam during initial examination was 0.88 ± 0.9 in the group of athletes and 1.92 ± 1.18 in the control group. Conclusion: The results of our study confirmed assumption concerning statistically significant incidence of standard hand arches in climbers. The character of climbing activity supports assumption about impact of the character of daily activities on the musculoskeletal system of climbers. Some physiotherapeutic methods use maintenance of hand arch in press-up position in order to improve techniques and performance of athletes.Aim: Finding out the state of hand arches in press-up positions in a selected sample of participants in relation to their sporting activities. Method: 29 participants took part in the study. The group of athletes consisted of 14 participantsi.e. 12 men and 2 women, age 27 ± 4.4, BMI 22 ± 2kg, frequency of training: 5 ± 1 per week. The control group included 15 participants from the general population, i.e. 8 men and 7 women age 23 ± 2.3, BMI 21.9 ± 2.2 working out no more than once a week without ambition to become professional athletes. The data was analysed in Microsoft Excel 2016 and in Control Freak programme (developed by Contchart Software company), particularly assessment by Shapiro -Wilk test. Results: The average value measured at PodoCam during initial examination was 0.88 ± 0.9 in the group of athletes and 1.92 ± 1.18 in the control group. Conclusion: The results of our study confirmed assumption concerning statistically significant incidence of standard hand arches in climbers. The character o...","PeriodicalId":20565,"journal":{"name":"PROCEEDINGS OF THE INTERNATIONAL CONFERENCE OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2019 (ICCMSE-2019)","volume":"383 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77691921","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}

{"title":"A study on accelerating convolutional neural networks","authors":"Hsien-I Lin, Chung-Sheng Cheng","doi":"10.1063/1.5138068","DOIUrl":"https://doi.org/10.1063/1.5138068","url":null,"abstract":"Recent deep-learning methods have been paid more attention than shallow-learning ones because they have deep and complex structures to approximate functions. The salient feature of deep neural networks is to use many layers where many of them are used to extract data features and few are for classification or regression. The most severe problem of a deep neural network is using too many parameters that cause too much memory usage and computing resources for both training and inference. Thus, deep learning approaches are not suitable for real-time industrial applications that have limited computing resources such as memory and CPU. For example, a famous convolutional neural network (CNN), AlexNet, uses up to 60 million parameters to train ImageNet dataset and many imaging projects apply AlexNet to their own applications as transfer learning. Thus, this work proposes a feasible solution to trim the CNN, speed it up, and keep the accuracy rate similar. Two main types of CNNs and AlexNet, were validated, respectively, in THUR15K, Caltech-101, Caltech-256, and GHIM10k datasets. The results show that the parameter amount greatly decreased (76%) but the recognition rate dropped slightly (1.34%).Recent deep-learning methods have been paid more attention than shallow-learning ones because they have deep and complex structures to approximate functions. The salient feature of deep neural networks is to use many layers where many of them are used to extract data features and few are for classification or regression. The most severe problem of a deep neural network is using too many parameters that cause too much memory usage and computing resources for both training and inference. Thus, deep learning approaches are not suitable for real-time industrial applications that have limited computing resources such as memory and CPU. For example, a famous convolutional neural network (CNN), AlexNet, uses up to 60 million parameters to train ImageNet dataset and many imaging projects apply AlexNet to their own applications as transfer learning. Thus, this work proposes a feasible solution to trim the CNN, speed it up, and keep the accuracy rate similar. Two main types of CNNs and AlexNet, were validated, resp...","PeriodicalId":20565,"journal":{"name":"PROCEEDINGS OF THE INTERNATIONAL CONFERENCE OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2019 (ICCMSE-2019)","volume":"7 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90684871","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}

{"title":"Computational formula for the impact of stochastic dependence on the insurance premium","authors":"J. Cha, Hyunju Lee, M. Finkelstein","doi":"10.1063/1.5138087","DOIUrl":"https://doi.org/10.1063/1.5138087","url":null,"abstract":"Standard actuarial theory of multiple life insurance traditionally postulates independence for the remaining lifetimes mainly due to computational convenience rather than realism. In this paper, we propose a general common shock model for modelling dependent coupled lives and apply it to a life insurance model. Under the model, we derive the computational formula for the impact of stochastic dependence on the pricings of insurance policies involving multiple lives which are subject to common shocks.Standard actuarial theory of multiple life insurance traditionally postulates independence for the remaining lifetimes mainly due to computational convenience rather than realism. In this paper, we propose a general common shock model for modelling dependent coupled lives and apply it to a life insurance model. Under the model, we derive the computational formula for the impact of stochastic dependence on the pricings of insurance policies involving multiple lives which are subject to common shocks.","PeriodicalId":20565,"journal":{"name":"PROCEEDINGS OF THE INTERNATIONAL CONFERENCE OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2019 (ICCMSE-2019)","volume":"43 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90897382","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}

{"title":"Development of information model and methods of data analysis on land taxation objects for Yekaterinburg city of Russia","authors":"V. Kalinin, A. Ilyin, A. Ilyina, N. Demin, A. Medvedev, Y. Kharitonov","doi":"10.1063/1.5137951","DOIUrl":"https://doi.org/10.1063/1.5137951","url":null,"abstract":"The work is devoted to the use of information technology in the taxation system at the municipal level. As a result of the study, an information model was created and the characteristics of the land taxation objects of Yekaterinburg, Russia were analyzed. It has been proposed to use Shewhart control chart to single out a group of objects, the amount of land tax for which ones is formed for special reasons of non-random and non-market character. It was shown that for the city of Yekaterinburg, in the aggregate of land taxation objects, fractal structures with different fractal dimension can be distinguished. It was proposed to divide and group objects of taxation using the fractal dimension to optimize the procedure for calculating the tax sizes.","PeriodicalId":20565,"journal":{"name":"PROCEEDINGS OF THE INTERNATIONAL CONFERENCE OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2019 (ICCMSE-2019)","volume":"76 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86654355","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}

{"title":"The course of hydrological drought in the river Drawa catchment (Northern Poland) as characterized by the standardized runoff index","authors":"Katarzyna Kubiak-Wójcicka","doi":"10.1063/1.5138035","DOIUrl":"https://doi.org/10.1063/1.5138035","url":null,"abstract":"The paper presents the course of hydrological droughts in the Drawa River catchment in the period of 1981– 2010. The study utilizes daily values of the Drawa’s discharge recorded in the Drawiny hydrological station and and daily values precipitation in two meteorological stations (Wierzchowo and Krzyz). Hydrological drought characteristics have been determined on the basis of the Standardized Runoff Index (SRI), which is a common hydrological drought index. SRI values were calculated on the basis of average monthly discharges that were accumulated in 1-, 3-, 6-, 9-, and 12-month periods. The most acute hydrological droughts in the analysed multi-annual period occurred in the years 2003– 2007.","PeriodicalId":20565,"journal":{"name":"PROCEEDINGS OF THE INTERNATIONAL CONFERENCE OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2019 (ICCMSE-2019)","volume":"48 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87037250","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}

{"title":"Preface of the Symposium “Traffic Infrastructure and Modelling” (TIAM-19)","authors":"T. Campisi, D. Ticali, A. Deluka-Tibljaš, Sanja Šurdonja","doi":"10.1063/1.5138069","DOIUrl":"https://doi.org/10.1063/1.5138069","url":null,"abstract":"","PeriodicalId":20565,"journal":{"name":"PROCEEDINGS OF THE INTERNATIONAL CONFERENCE OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2019 (ICCMSE-2019)","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83780269","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}

{"title":"Preface of the International Symposium on Computer Science and Information Technology (ISCSIT 2019)","authors":"M. Kotyrba, E. Volná, V. Bradác, M. Žáček, Bogdan Walek","doi":"10.1063/1.5137955","DOIUrl":"https://doi.org/10.1063/1.5137955","url":null,"abstract":"","PeriodicalId":20565,"journal":{"name":"PROCEEDINGS OF THE INTERNATIONAL CONFERENCE OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2019 (ICCMSE-2019)","volume":"19 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81876173","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}

{"title":"Climate change driven events and projects’ vulnerability as element of the EIA procedure – Application of the IAEA STE selection criteria","authors":"R. Urbaniak, D. Absalon","doi":"10.1063/1.5138042","DOIUrl":"https://doi.org/10.1063/1.5138042","url":null,"abstract":"There is a clear cause-and-effect interaction at play between environment and the project itself that acts two-way, making the project’s suitable site selection of utmost importance. As general public becomes more and more aware of environmental issues that need to be addressed in the course of licensing procedures (Environmental Impact Assessment [EIA]) many aspects that can affect a planned development’s site suitability remain hidden from the public view and yet crucial as they can determine investment’s not only impact spatial boundaries but even its viability. Determination of a planned development’s location, therefore, should be preceded by detailed siting and environmental studies completing of which guarantee removal or at least occurrence probability reduction from a financial equation of significant uncertainties that could impact an investment at either the designing or operating stage. In the paper application of conventional energy sector methodologies as well as site selection criteria of the Safety Standards, International Atomic Energy Agency [IAEA] for nuclear installations as mutually complementing tools are being discussed with a special consideration given to climatic, geological and legislative issues.There is a clear cause-and-effect interaction at play between environment and the project itself that acts two-way, making the project’s suitable site selection of utmost importance. As general public becomes more and more aware of environmental issues that need to be addressed in the course of licensing procedures (Environmental Impact Assessment [EIA]) many aspects that can affect a planned development’s site suitability remain hidden from the public view and yet crucial as they can determine investment’s not only impact spatial boundaries but even its viability. Determination of a planned development’s location, therefore, should be preceded by detailed siting and environmental studies completing of which guarantee removal or at least occurrence probability reduction from a financial equation of significant uncertainties that could impact an investment at either the designing or operating stage. In the paper application of conventional energy sector methodologies as well as site selection criteria of t...","PeriodicalId":20565,"journal":{"name":"PROCEEDINGS OF THE INTERNATIONAL CONFERENCE OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2019 (ICCMSE-2019)","volume":"39 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74270386","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}