Language models have contributed to breakthroughs in interdisciplinary research,such as protein design and molecular dynamics understanding.In this study,we reveal that beyond language,representations of other entitie...Language models have contributed to breakthroughs in interdisciplinary research,such as protein design and molecular dynamics understanding.In this study,we reveal that beyond language,representations of other entities,such as human behaviors,that are mappable to learmable se quences can be learned by language models.One compelling example is the realworld delivery route optimization problem.We here propose a novel approach based on the language model to optimize delivery routes on the basis of drivers'historical experiences.Although a broad range of optimizationbased approaches have been designed to optimize delivery routes,they do not capture the implicit knowledge of complex delivery operating environments.The model we propose integrates this knowledge in the route optimization process by learning from driving behaviors in experienced drivers.A real-world delivery route that preserves drivers'implicit behavioral patterns is first analogized to a sentence in natural language.Through unsupervised learning,we then learn the vector representations of words and infer the drivers'delivery chains on the basis of the tailored chain-reaction-based algorithm.We also provide insights into the fusion of language models and operations research methods.In our approach,language models are applied to learn drivers'delivery behaviors and infer new deliveries at the delivery zone level,while the classic traveling salesman problem(TSP)model is embedded into the hybrid framework for intra-zone optimization.Numerical experiments performed on real-world data from Amazon's delivery service demonstrate that the proposed approach outperforms pure optimization,supporting the effectiveness,efficiency,and extensibility of our model.As a versatile approach,the proposed framework can easily be extended to various disciplines in which the data follow cert ain grammar rules.We anticipate that our work will serve as a stepping stone toward the understanding and application of language models in tackling interdisciplinary research problems.展开更多
Tree-ring dating enables gathering necessary knowledge about trees,and it is essential in many areas,including forest management and the timber industry.Tree-ring dating can be conducted on either wood’s clean crosss...Tree-ring dating enables gathering necessary knowledge about trees,and it is essential in many areas,including forest management and the timber industry.Tree-ring dating can be conducted on either wood’s clean crosssections or tree trunks’rough end cross-sections.However,the measurement process is still time-consuming and frequently requires experts who use special devices,such as stereoscopes.Modern approaches based on image processing using deep learning have been successfully applied in many areas,and they can succeed in recognizing tree rings.While supervised deep learning-based methods often produce excellent results,they also depend on extensive datasets of tediously annotated data.To our knowledge,there are only a few publicly available ring image datasets with annotations.We introduce a new carefully captured dataset of images of hardwood species automatically annotated for tree ring detection.We capture each wood cookie twice,once in the rough form,similar to industrial settings,and then after careful cleaning,that reveals all growth rings.We carefully overlap the images and use them for an automatic ring annotation in the rough data.We then use the Feature Pyramid Network with Resnet encoder that obtains an overall pixel-level area under the curve score of 85.72%and ring level F_(1) score of 0.7348.The data and code are available at https://github.com/wufanyou/growth-ring-detection.展开更多
基金National Natural Science Foundation of China(grants 72322002,52221005,and 52220105001).
文摘Language models have contributed to breakthroughs in interdisciplinary research,such as protein design and molecular dynamics understanding.In this study,we reveal that beyond language,representations of other entities,such as human behaviors,that are mappable to learmable se quences can be learned by language models.One compelling example is the realworld delivery route optimization problem.We here propose a novel approach based on the language model to optimize delivery routes on the basis of drivers'historical experiences.Although a broad range of optimizationbased approaches have been designed to optimize delivery routes,they do not capture the implicit knowledge of complex delivery operating environments.The model we propose integrates this knowledge in the route optimization process by learning from driving behaviors in experienced drivers.A real-world delivery route that preserves drivers'implicit behavioral patterns is first analogized to a sentence in natural language.Through unsupervised learning,we then learn the vector representations of words and infer the drivers'delivery chains on the basis of the tailored chain-reaction-based algorithm.We also provide insights into the fusion of language models and operations research methods.In our approach,language models are applied to learn drivers'delivery behaviors and infer new deliveries at the delivery zone level,while the classic traveling salesman problem(TSP)model is embedded into the hybrid framework for intra-zone optimization.Numerical experiments performed on real-world data from Amazon's delivery service demonstrate that the proposed approach outperforms pure optimization,supporting the effectiveness,efficiency,and extensibility of our model.As a versatile approach,the proposed framework can easily be extended to various disciplines in which the data follow cert ain grammar rules.We anticipate that our work will serve as a stepping stone toward the understanding and application of language models in tackling interdisciplinary research problems.
基金supported by a McIntire Stennis grant(accession No.1012928)to Gazo from the USDA National Institute of Food and Agriculture and a grant from the Purdue University Hardwood Tree Improvement and Regeneration Center and the Foundation for Food and Agriculture Research,United States(Grant ID:602757)to Benes.
文摘Tree-ring dating enables gathering necessary knowledge about trees,and it is essential in many areas,including forest management and the timber industry.Tree-ring dating can be conducted on either wood’s clean crosssections or tree trunks’rough end cross-sections.However,the measurement process is still time-consuming and frequently requires experts who use special devices,such as stereoscopes.Modern approaches based on image processing using deep learning have been successfully applied in many areas,and they can succeed in recognizing tree rings.While supervised deep learning-based methods often produce excellent results,they also depend on extensive datasets of tediously annotated data.To our knowledge,there are only a few publicly available ring image datasets with annotations.We introduce a new carefully captured dataset of images of hardwood species automatically annotated for tree ring detection.We capture each wood cookie twice,once in the rough form,similar to industrial settings,and then after careful cleaning,that reveals all growth rings.We carefully overlap the images and use them for an automatic ring annotation in the rough data.We then use the Feature Pyramid Network with Resnet encoder that obtains an overall pixel-level area under the curve score of 85.72%and ring level F_(1) score of 0.7348.The data and code are available at https://github.com/wufanyou/growth-ring-detection.
