An efficient numerical approach for the general thermomechanical problems was developed and it was tested for a two-dimensional thermoelasticity problem. The main idea of our numerical method is based on the reduction...An efficient numerical approach for the general thermomechanical problems was developed and it was tested for a two-dimensional thermoelasticity problem. The main idea of our numerical method is based on the reduction procedure of the original system of PDEs describing coupled thermomechanical behavior to a system of Differential Algebraic Equations （DAEs） where the stress-strain relationships are treated as algebraic equations. The resulting system of DAEs was then solved with a Backward Differentiation Formula （BDF） using a fully implicit algorithm. The described procedure was explained in detail, and its effectiveness was demonstrated on the solution of a transient uncoupled thermoelastic problem, for which an analytical solution is known, as well as on a fully coupled problem in the two-dimensional case.展开更多
The convolutional neural network(CNN)is one of the main algorithms that is applied to deep transfer learning for classifying two essential types of liver lesions;Hemangioma and hepatocellular carcinoma(HCC).Ultrasound...The convolutional neural network(CNN)is one of the main algorithms that is applied to deep transfer learning for classifying two essential types of liver lesions;Hemangioma and hepatocellular carcinoma(HCC).Ultrasound images,which are commonly available and have low cost and low risk compared to computerized tomography(CT)scan images,will be used as input for the model.A total of 350 ultrasound images belonging to 59 patients are used.The number of images with HCC is 202 and 148,respectively.These images were collected from ultrasound cases.info(28 Hemangiomas patients and 11 HCC patients),the department of radiology,the University of Washington(7 HCC patients),the Atlas of ultrasound Germany(3 HCC patients),and Radiopedia and others(10 HCC patients).The ultrasound images are divided into 225,52,and 73 for training,validation,and testing.A data augmentation technique is used to enhance the validation performance.We proposed an approach based on ensembles of the best-selected deep transfer models from the on-the-shelf models:VGG16,VGG19,DenseNet,Inception,InceptionResNet,ResNet,and EfficientNet.After tuning both the feature extraction and the classification layers,the best models are selected.Validation accuracy is used for model tuning and selection.The accuracy,sensitivity,specificity and AUROC are used to evaluate the performance.The experiments are concluded in five stages.The first stage aims to evaluate the base model performance by training the on-the-shelf models.The best accu-racy obtained in the first stage is 83.5%.In the second stage,we augmented the data and retrained the on-the-shelf models with the augmented data.The best accuracy we obtained in the second stage was 86.3%.In the third stage,we tuned the feature extraction layers of the on-the-shelf models.The best accuracy obtained in the third stage is 89%.In the fourth stage,we fine-tuned the classification layer and obtained an accuracy of 93%as the best accuracy.In the fifth stage,we applied the ensemble approach using the best three-performing models and obtained an accuracy,specificity,sensitivity,and AUROC of 94%,93.7%,95.1%,and 0.944,respectively.展开更多
In order to substitute fossil resources in activated carbon(AC)production,recent efforts have focused on the utilization of renewable raw materials.Regions with important wood industries offer two potentially underest...In order to substitute fossil resources in activated carbon(AC)production,recent efforts have focused on the utilization of renewable raw materials.Regions with important wood industries offer two potentially underestimated resource types:forestry residue biomass(FRB)and waste wood(WW).Although these materials are widely available(approx.130 mio.m3a-1 FRB,approx.50 mio.ta^(-1) WW in the EU),they are mostly valorised through energy production,as they are high in ashes and may be contaminated with organics and heavy metals.In this study,both FRB and WW were treated via one-step pyrolysis for AC production.ZnCl_(2) was applied as activating agent at pyrolysis temperatures varying from 400 to 600℃ and residence times between 1 and 3 h.Overall,76 samples were prepared and characterized thoroughly via elemental analysis,N_(2)/CO_(2) ad/-desorption,thermogravimetric analysis(TGA),scanning electron microscopy(SEM),and infrared spectroscopy(FTIR).The produced carbons showed specific surface areas of up to 1430 m2g1 and a pore size distribution with a micropore share of up to 80%.The presence of oxygen-containing functional groups was confirmed via FTIR.Potential feedstock contamination can be mitigated,as minerals and heavy metals could be leached out(up to-99.15%)by an additional wash step and organic contamination undergoes thermal cracking during pyrolysis.The presented study could be a next step in upcycling considerable waste streams from the wood sector through localised and non-fossil-based AC production.展开更多
文摘An efficient numerical approach for the general thermomechanical problems was developed and it was tested for a two-dimensional thermoelasticity problem. The main idea of our numerical method is based on the reduction procedure of the original system of PDEs describing coupled thermomechanical behavior to a system of Differential Algebraic Equations （DAEs） where the stress-strain relationships are treated as algebraic equations. The resulting system of DAEs was then solved with a Backward Differentiation Formula （BDF） using a fully implicit algorithm. The described procedure was explained in detail, and its effectiveness was demonstrated on the solution of a transient uncoupled thermoelastic problem, for which an analytical solution is known, as well as on a fully coupled problem in the two-dimensional case.
基金funded by the Deanship of Scientific Research at Jouf University under Grant No.(DSR-2022-RG-0104).
文摘The convolutional neural network(CNN)is one of the main algorithms that is applied to deep transfer learning for classifying two essential types of liver lesions;Hemangioma and hepatocellular carcinoma(HCC).Ultrasound images,which are commonly available and have low cost and low risk compared to computerized tomography(CT)scan images,will be used as input for the model.A total of 350 ultrasound images belonging to 59 patients are used.The number of images with HCC is 202 and 148,respectively.These images were collected from ultrasound cases.info(28 Hemangiomas patients and 11 HCC patients),the department of radiology,the University of Washington(7 HCC patients),the Atlas of ultrasound Germany(3 HCC patients),and Radiopedia and others(10 HCC patients).The ultrasound images are divided into 225,52,and 73 for training,validation,and testing.A data augmentation technique is used to enhance the validation performance.We proposed an approach based on ensembles of the best-selected deep transfer models from the on-the-shelf models:VGG16,VGG19,DenseNet,Inception,InceptionResNet,ResNet,and EfficientNet.After tuning both the feature extraction and the classification layers,the best models are selected.Validation accuracy is used for model tuning and selection.The accuracy,sensitivity,specificity and AUROC are used to evaluate the performance.The experiments are concluded in five stages.The first stage aims to evaluate the base model performance by training the on-the-shelf models.The best accu-racy obtained in the first stage is 83.5%.In the second stage,we augmented the data and retrained the on-the-shelf models with the augmented data.The best accuracy we obtained in the second stage was 86.3%.In the third stage,we tuned the feature extraction layers of the on-the-shelf models.The best accuracy obtained in the third stage is 89%.In the fourth stage,we fine-tuned the classification layer and obtained an accuracy of 93%as the best accuracy.In the fifth stage,we applied the ensemble approach using the best three-performing models and obtained an accuracy,specificity,sensitivity,and AUROC of 94%,93.7%,95.1%,and 0.944,respectively.
基金The financial support by the Austrian Federal Ministry for Digital and Economic Affairs and the National Foundation for Research,Technology and Development,the Christian Doppler Research Association as well as the participating companies is gratefully acknowledged.
文摘In order to substitute fossil resources in activated carbon(AC)production,recent efforts have focused on the utilization of renewable raw materials.Regions with important wood industries offer two potentially underestimated resource types:forestry residue biomass(FRB)and waste wood(WW).Although these materials are widely available(approx.130 mio.m3a-1 FRB,approx.50 mio.ta^(-1) WW in the EU),they are mostly valorised through energy production,as they are high in ashes and may be contaminated with organics and heavy metals.In this study,both FRB and WW were treated via one-step pyrolysis for AC production.ZnCl_(2) was applied as activating agent at pyrolysis temperatures varying from 400 to 600℃ and residence times between 1 and 3 h.Overall,76 samples were prepared and characterized thoroughly via elemental analysis,N_(2)/CO_(2) ad/-desorption,thermogravimetric analysis(TGA),scanning electron microscopy(SEM),and infrared spectroscopy(FTIR).The produced carbons showed specific surface areas of up to 1430 m2g1 and a pore size distribution with a micropore share of up to 80%.The presence of oxygen-containing functional groups was confirmed via FTIR.Potential feedstock contamination can be mitigated,as minerals and heavy metals could be leached out(up to-99.15%)by an additional wash step and organic contamination undergoes thermal cracking during pyrolysis.The presented study could be a next step in upcycling considerable waste streams from the wood sector through localised and non-fossil-based AC production.
