Auto-grading,as an instruction tool,could reduce teachers’workload,provide students with instant feedback and support highly personalized learning.Therefore,this topic attracts considerable attentions from researcher...Auto-grading,as an instruction tool,could reduce teachers’workload,provide students with instant feedback and support highly personalized learning.Therefore,this topic attracts considerable attentions from researchers recently.To realize the automatic grading of handwritten chemistry assignments,the problem of chemical notations recognition should be solved first.The recent handwritten chemical notations recognition solutions belonging to the end-to-end trainable category suffered fromthe problem of lacking the accurate alignment information between the input and output.They serve the aim of reading notations into electrical devices to better prepare relevant edocuments instead of auto-grading handwritten assignments.To tackle this limitation to enable the auto-grading of handwritten chemistry assignments at a fine-grained level.In this work,we propose a component-detectionbased approach for recognizing off-line handwritten Organic Cyclic Compound Structure Formulas(OCCSFs).Specifically,we define different components of OCCSFs as objects(including graphical objects and text objects),and adopt the deep learning detector to detect them.Then,regarding the detected text objects,we introduce an improved attention-based encoder-decoder model for text recognition.Finally,with these detection results and the geometric relationships of detected objects,this article designs a holistic algorithm for interpreting the spatial structure of handwritten OCCSFs.The proposedmethod is evaluated on a self-collected data set consisting of 3000 samples and achieves promising results.展开更多
Titanium alloys are composed ofαandβphases and are classified as nearα,dual-phaseα+β,andβtypes.This study attempts to derive their general composition formulas within the cluster-plus-glue-atom model by interpre...Titanium alloys are composed ofαandβphases and are classified as nearα,dual-phaseα+β,andβtypes.This study attempts to derive their general composition formulas within the cluster-plus-glue-atom model by interpreting Ti-6A1-4V and other popular dual-phaseα+βTi alloy s with well-established chemical compositions.Our model identifiedαmolecule-like structural unit that covers onlyαnearest-neighbor cluster along withαfew next-neighbor glue atoms,which can be represented as"[cluster](glue atoms)x".The structural units of theαandβphases in Ti-6Al-4V,α-[Al-Ti_(12)](AlTi_(2)),andβ-[Al-Ti_(14)](V2Ti),were derived first and were in an unusual unit ratio of about 2.33:1.To obtain an alloy composition formula that satisfied this unit ratio,the two clusters were treated as hard spheres of different radii and packed according to the clusterplusglueatom model.Our calculations determined that the Ti-6A1-4V alloy unit is composed of 12α-[Al-Ti_(12)](AlTi_(2))and 5β-[Al-Ti_(14)](V2Ti)units(Ti-6.05A1-3.94V wt.%),with the fractional volume of theβphase being 32.5 vol.%,which is in agreement with experimental data.Finally,we describe how the chemical formulas of theαand p phases explain the high temperature near-a alloys(such as Ti-1100,[Al-(Ti_(0.97)Zr_(0.03))_(12)](Al_(0.67)Si_(0.12)Sn_(0.18)Mo_(0.03))_(1.01)Ti_(1.99))and high-strengthβ-Ti alloys(such as Ti-5553,[Al-Ti_(14)](Al_(0.24)Fe_(0.03)Cr_(0.20)-Mo_(0.18)V0.35)_(2.45)Ti_(0.55)),respectively.展开更多
基金supported by National Natural Science Foundation of China (Nos.62007014 and 62177024)the Humanities and Social Sciences Youth Fund of the Ministry of Education (No.20YJC880024)+1 种基金China Post Doctoral Science Foundation (No.2019M652678)the Fundamental Research Funds for the Central Universities (No.CCNU20ZT019).
文摘Auto-grading,as an instruction tool,could reduce teachers’workload,provide students with instant feedback and support highly personalized learning.Therefore,this topic attracts considerable attentions from researchers recently.To realize the automatic grading of handwritten chemistry assignments,the problem of chemical notations recognition should be solved first.The recent handwritten chemical notations recognition solutions belonging to the end-to-end trainable category suffered fromthe problem of lacking the accurate alignment information between the input and output.They serve the aim of reading notations into electrical devices to better prepare relevant edocuments instead of auto-grading handwritten assignments.To tackle this limitation to enable the auto-grading of handwritten chemistry assignments at a fine-grained level.In this work,we propose a component-detectionbased approach for recognizing off-line handwritten Organic Cyclic Compound Structure Formulas(OCCSFs).Specifically,we define different components of OCCSFs as objects(including graphical objects and text objects),and adopt the deep learning detector to detect them.Then,regarding the detected text objects,we introduce an improved attention-based encoder-decoder model for text recognition.Finally,with these detection results and the geometric relationships of detected objects,this article designs a holistic algorithm for interpreting the spatial structure of handwritten OCCSFs.The proposedmethod is evaluated on a self-collected data set consisting of 3000 samples and achieves promising results.
基金supported by the National Key Research and Development Program of China(Grant No.2016YFB1100103)the Science Research Project of Liaoning Province Education Department(Grant No.JDL2019023)+1 种基金the Natural Science Foundation of Liaoning Province(Grant No.2020-BS-208)the Open Project of Key Laboratory of Materials Modification by Laser,Ion and Electron Beams(Grant No.KF2006)。
文摘Titanium alloys are composed ofαandβphases and are classified as nearα,dual-phaseα+β,andβtypes.This study attempts to derive their general composition formulas within the cluster-plus-glue-atom model by interpreting Ti-6A1-4V and other popular dual-phaseα+βTi alloy s with well-established chemical compositions.Our model identifiedαmolecule-like structural unit that covers onlyαnearest-neighbor cluster along withαfew next-neighbor glue atoms,which can be represented as"[cluster](glue atoms)x".The structural units of theαandβphases in Ti-6Al-4V,α-[Al-Ti_(12)](AlTi_(2)),andβ-[Al-Ti_(14)](V2Ti),were derived first and were in an unusual unit ratio of about 2.33:1.To obtain an alloy composition formula that satisfied this unit ratio,the two clusters were treated as hard spheres of different radii and packed according to the clusterplusglueatom model.Our calculations determined that the Ti-6A1-4V alloy unit is composed of 12α-[Al-Ti_(12)](AlTi_(2))and 5β-[Al-Ti_(14)](V2Ti)units(Ti-6.05A1-3.94V wt.%),with the fractional volume of theβphase being 32.5 vol.%,which is in agreement with experimental data.Finally,we describe how the chemical formulas of theαand p phases explain the high temperature near-a alloys(such as Ti-1100,[Al-(Ti_(0.97)Zr_(0.03))_(12)](Al_(0.67)Si_(0.12)Sn_(0.18)Mo_(0.03))_(1.01)Ti_(1.99))and high-strengthβ-Ti alloys(such as Ti-5553,[Al-Ti_(14)](Al_(0.24)Fe_(0.03)Cr_(0.20)-Mo_(0.18)V0.35)_(2.45)Ti_(0.55)),respectively.
