Purpose:To develop and validate an artificialintelligence model based on focused assessment with sonography for trauma(FAST)for the semi-quantitative grading of intra-abdominal hemorrhage resulting from blunt abdomina...Purpose:To develop and validate an artificialintelligence model based on focused assessment with sonography for trauma(FAST)for the semi-quantitative grading of intra-abdominal hemorrhage resulting from blunt abdominal trauma,particularly for use in prehospital or resource-limited settings.Methods:Nine Bama miniature pigs,mean weight(31.46±3.73)kg were enrolled.Graded hemorrhage from 0 to 1000 mL was simulated by infusing 100 mL of autologous arterial blood into the peritoneal cavity at each step.The hemorrhage volume was mapped to 3 grades based on total blood volume(estimated at 65 mL/kg):Grade Ⅰ(30%).FAST ultrasound videos were acquired from 6 standard sites:right upper quadrant-1,right upper quadrant-2,left upper quadrant-1,left upper quadrant-2,right pelvic cavity,and left pelvic cavity.The pixel area of hemorrhage was obtained by manually segmenting the frame with the largest fluidcollection using ITK-SNAP,and the corresponding scanning depth was recorded.A linear mixed-effects model was used to assess the impact of scanning depth on pixel area.A deep neural network,incorporating class weighting and dynamic probability threshold optimization,was constructed using a multimodal feature set including animal weight,pixel areas and scanning depths from each site,and the total pixel area.A 3-grade classificationwas performed.The model's performance was evaluated using leave-one-out cross-validation on an animal basis and compared with logistic regression,random forest,gradient boosting decision tree,and support vector machine.Results:A total of 797 raw videos were acquired,with 522 videos comprising 87 data groups(each covering 6 sites)included after screening.As hemorrhage volume increased,heart rate and shock index rose,while systolic blood pressure decreased;at 800 mL of hemorrhage,the shock index was 2.31±0.38.The mixed-effects model revealed a significantnegative correlation between scanning depth and pixel area(β=-2099.00,SE=1041.13,z=-2.02,p=0.044).The proposed model achieved an overall accuracy of 81.19%,outperforming support vector machine(73.77%),gradient boosting decision tree(70.63%),random forest(69.52%),and logistic regression(65.99%).Conclusion:In a porcine model of blunt abdominal trauma,a multimodal artificialintelligence approach based on FAST multi-site pixel area features,combined with a deep neural network optimized by class weighting and dynamic probability thresholds,can achieve semi-quantitative grading of intraabdominal hemorrhage.展开更多
1.Introduction Scramjet is pivotal for achieving hypersonic flight,enabling vehicles to operate at speeds exceeding Mach number 5.This engine is crucial for next-generation aerospace systems,including hypersonic missi...1.Introduction Scramjet is pivotal for achieving hypersonic flight,enabling vehicles to operate at speeds exceeding Mach number 5.This engine is crucial for next-generation aerospace systems,including hypersonic missiles,spaceplanes,and high-speed aircraft.However,the development of scramjet is fraught with significant technical challenges,such as supersonic combustion,thermal management,and dynamic flow control.展开更多
The biological stabilization of soil using microbially induced carbonate precipitation(MICP)employs ureolytic bacteria to precipitate calcium carbonate(CaCO3),which binds soil particles,enhancing strength,stiffness,an...The biological stabilization of soil using microbially induced carbonate precipitation(MICP)employs ureolytic bacteria to precipitate calcium carbonate(CaCO3),which binds soil particles,enhancing strength,stiffness,and erosion resistance.The unconfinedcompressive strength(UCS),a key measure of soil strength,is critical in geotechnical engineering as it directly reflectsthe mechanical stability of treated soils.This study integrates explainable artificialintelligence(XAI)with geotechnical insights to model the UCS of MICP-treated sands.Using 517 experimental data points and a combination of various input variables—including median grain size(D50),coefficientof uniformity(Cu),void ratio(e),urea concentration(Mu),calcium concentration(Mc),optical density(OD)of bacterial solution,pH,and total injection volume(Vt)—fivemachine learning(ML)models,including eXtreme gradient boosting(XGBoost),Light gradient boosting machine(LightGBM),random forest(RF),gene expression programming(GEP),and multivariate adaptive regression splines(MARS),were developed and optimized.The ensemble models(XGBoost,LightGBM,and RF)were optimized using the Chernobyl disaster optimizer(CDO),a recently developed metaheuristic algorithm.Of these,LightGBM-CDO achieved the highest accuracy for UCS prediction.XAI techniques like feature importance analysis(FIA),SHapley additive exPlanations(SHAP),and partial dependence plots(PDPs)were also used to investigate the complex non-linear relationships between the input and output variables.The results obtained have demonstrated that the XAI-driven models can enhance the predictive accuracy and interpretability of MICP processes,offering a sustainable pathway for optimizing geotechnical applications.展开更多
1 Introduction Artificial intelligence(Al)has rapidly emerged as a transformative force across the chemical engineering field.From academia to industry,chemical engineers are leveraging data-driven models and advanced...1 Introduction Artificial intelligence(Al)has rapidly emerged as a transformative force across the chemical engineering field.From academia to industry,chemical engineers are leveraging data-driven models and advanced algorithms to optimize production,enhance safety,design novel processes and materials,and even generate new scientific insights.In recent years,the number of publications and projects applying machine learning(ML)and AI in process systems engineering(PSE),industrial data science,and chemical engineering more broadly has skyrocketed[1-3].展开更多
Diverse energy and power systems have been playing a significantly critical role in the revolution of sustainable energy supply for the future,which have a great impact on energy resources and efficiencies.Due to the ...Diverse energy and power systems have been playing a significantly critical role in the revolution of sustainable energy supply for the future,which have a great impact on energy resources and efficiencies.Due to the emerging artificial intelligence and machine learning,traditional modeling techniques in these energy systems have met challenges in still leveraging physics model and first principle-based approaches.Moreover,with the rapid development of hardware and computing techniques,new modeling approaches for energy systems have become more and more important for system design,integration,analysis,control,and management.展开更多
The rapid advancement of artificial intelligence(AI)technologies,particularly the groundbreaking progress of large language models(LLMs)in the field of the natural language processing,has been profoundly reshaping the...The rapid advancement of artificial intelligence(AI)technologies,particularly the groundbreaking progress of large language models(LLMs)in the field of the natural language processing,has been profoundly reshaping the scientific research paradigms.展开更多
The integration of artificial intelligence(AI)with biomedical optical imaging has emerged as one of the most transformative directions in modern biophotonics.From accelerating image reconstruction to enhancing quantit...The integration of artificial intelligence(AI)with biomedical optical imaging has emerged as one of the most transformative directions in modern biophotonics.From accelerating image reconstruction to enhancing quantitative analysis,AI-driven approaches are reshaping how we acquire,process,and interpret optical imaging data across scales—from subcellular structures to whole organisms.Deep learning,in particular,has demonstrated remarkable capacity to address long-standing challenges in computational imaging,including noise suppression,artifact correction,super-resolution reconstruction,and multi-modal data fusion.展开更多
The conceptual framework for the hallmarks of cancer,which was first proposed by Hanahan and Weinberg in 20001 and updated in 20112 and 2022,3 with a more recent version published in the spring of 2026,is the foundati...The conceptual framework for the hallmarks of cancer,which was first proposed by Hanahan and Weinberg in 20001 and updated in 20112 and 2022,3 with a more recent version published in the spring of 2026,is the foundational blueprint of modern cancer research.This latest review moves beyond a simple list of tumor traits to organize the immense complexity of cancer into four interconnected dimensions.4 The first dimension concerns acquired capabilities,which are the core functional capabilities cancer cells need to survive and spread.展开更多
During the Two Sessions,members of the CPPCC National Committee and deputies to the NPC discussed issues of common concern in the standardization field,such as artificial intelligence(AI)and digital technologies,vehic...During the Two Sessions,members of the CPPCC National Committee and deputies to the NPC discussed issues of common concern in the standardization field,such as artificial intelligence(AI)and digital technologies,vehicles and new energy,construction engineering,as well as food and agricultural products.Here,we summarize their insights into standards,to help standards play a bigger role in vigorously promoting the Chinese modernization.展开更多
As 2026 unfolds,the image of an autonomous port in Ningbo loading a U.S.-bound ship encapsulates the transformative power of China’s surge in artificial intelligence(AI).This automation marvel not only symbolizes Ch...As 2026 unfolds,the image of an autonomous port in Ningbo loading a U.S.-bound ship encapsulates the transformative power of China’s surge in artificial intelligence(AI).This automation marvel not only symbolizes China’s economic power but also demonstrates how deeply integrated AI has become into its global competition strategy.Once largely confined to academic research and pilot programs,AI is now embedded in China’s national strategy.The goal:drive productivity,modernize industries,and strengthen its competitive position in global technology markets.展开更多
China Issues Three-year Plan to Boost AI Integration With Information,Communications Sector China’s Ministry of Industry and Information Technology recent1y re1eased a three-year p1an to accelerate the integration of...China Issues Three-year Plan to Boost AI Integration With Information,Communications Sector China’s Ministry of Industry and Information Technology recent1y re1eased a three-year p1an to accelerate the integration of artificial intelligence(AI)with the country's infor mation and communications sector,setting targets for more autonomous networks.展开更多
Seventy years ago,a handful of young scholars gathered at Dartmouth College in New Hampshire and first uttered the words“artificial intelligence.”Seven decades later,as algorithms begin to“think”and machines step ...Seventy years ago,a handful of young scholars gathered at Dartmouth College in New Hampshire and first uttered the words“artificial intelligence.”Seven decades later,as algorithms begin to“think”and machines step from the digital world into the physical one,the question is no longer whether AI will reshape human civilization,but who will write the score.展开更多
主题群:AI与艺术篇幅:317词建议用时:6分钟.1 Reflecting on a favorite piece of art—whether a painting,song,novel or film—often brings about deeply personal connections rooted in emotion,meaning and human experience.Now...主题群:AI与艺术篇幅:317词建议用时:6分钟.1 Reflecting on a favorite piece of art—whether a painting,song,novel or film—often brings about deeply personal connections rooted in emotion,meaning and human experience.Now,imagine that same work was generated by artificial intelligence.This situation is increasingly likely as AI rapidly evolves to produce works across creative fields like writing,visual art,music and choreography(编舞艺术).A recent survey sought to understand public views on this shift.展开更多
Over 25 years ago,Jeanologia revolutionized the denim industry by introducing laser technology for jean finishing,a solution that replaced manual processes with high impact on both workers’health and the environment,...Over 25 years ago,Jeanologia revolutionized the denim industry by introducing laser technology for jean finishing,a solution that replaced manual processes with high impact on both workers’health and the environment,marking the beginning of a new era in denim production.Today,the Spanish company is once again transforming the sector with the launch of BILLY,the first artificial intelligence developed specifically for the denim industry,capable of extracting precise designs directly from a picture.With this launch,Jeanologia brings AI into one of the most creative and complex phases of denim development:design.展开更多
1 Artificial intelligence(AI)has become a debated creative tool in todays art world.When it comes to AI in art,it is essential to examine different types and uses separately.Generative AI,which creates animated digita...1 Artificial intelligence(AI)has become a debated creative tool in todays art world.When it comes to AI in art,it is essential to examine different types and uses separately.Generative AI,which creates animated digital artworks,deserves special attention.2 Using AI to create art raises important ethical questions that both creators and viewers must consider carefully.One major concern involves intellectual property—who owns the artwork created by AI systems,especially when these systems learn from existing copyrighted works?Another critical issue is bias in training data.If AI learns from biased information,the generated art may strengthen unfair ideas about certain groups or fail to represent them fairly.展开更多
Trainers are shaping AI to respond with empathy,gentleness and emotional understanding “AI is my best friend,”24-yearold Yu Yang from the private training sector shared on social media.With its constant availability...Trainers are shaping AI to respond with empathy,gentleness and emotional understanding “AI is my best friend,”24-yearold Yu Yang from the private training sector shared on social media.With its constant availability,efficiency and rationality,AI has become a true source of emotional support for certain users.展开更多
In recent years,tunnel boring machines(TBMs)have been widely used in tunnel construction.Rockbursts,as a dynamic geological disaster,pose a serious threat to the safety and efficienttunneling of TBMs.The microseismic ...In recent years,tunnel boring machines(TBMs)have been widely used in tunnel construction.Rockbursts,as a dynamic geological disaster,pose a serious threat to the safety and efficienttunneling of TBMs.The microseismic monitoring technique provides an effective solution for rockburst warning.However,due to the complexity and variability of the TBM excavation environment,microseismic events induced by rock fracture are often accompanied by interference events,such as electrical noise,TBM vibration,and mechanical knock.This study proposes a multi-channel intelligent classification approach for microseismic events in TBM excavation scenarios,based on double-layer stacking learning,to identify rock fractures.In this approach,decision tree is used as the base classifieron each microseismic channel,while extreme learning machine is employed as the meta-classifierto aggregate all base classifiers.Additionally,mind evolutionary computation is integrated to optimize the built-in hyperparameters of various classifiers.Meanwhile,a comprehensive preprocessing and augmentation flowfor microseismic data has been developed,encompassing feature extraction,dimensionality reduction,outlier detection,and outlier substitution.The results reveal that the multi-channel stacking model,which combines classificationand regression tree and extreme learning machine,achieves optimal global and local generalization performance compared to other multi-channel stacking models and traditional single-channel models.The accuracy,Hamming loss,and Cohen’s kappa are 96.75%,0.0325,and 0.9148,respectively,and the F1-score and AUC on rock fracture events are 0.9366 and 0.9818,respectively.Finally,a generative artificialintelligence-based scheme is invented to enhance the robustness of the model for signal-mixing events.展开更多
1.Introduction Engineers,policymakers,and governments are currently facing the pressing global challenges of climate change and the energy crisis.To address the continuously increasing demand for energy and mitigate e...1.Introduction Engineers,policymakers,and governments are currently facing the pressing global challenges of climate change and the energy crisis.To address the continuously increasing demand for energy and mitigate environmental damage,energy conservation and emissions reduction have become strategic priorities for sustainable development[1].Nations worldwide have reached a consensus on reducing carbon emissions and have introduced various policies and actions,such as the carbon peak and carbon neutrality targets proposed by China[2,3].展开更多
The use of microalgae to recover nitrogen and phosphorus from wastewater has garnered significant attention,positioning it as one of the most promising and sustainable strategies in modern wastewater treatment.While v...The use of microalgae to recover nitrogen and phosphorus from wastewater has garnered significant attention,positioning it as one of the most promising and sustainable strategies in modern wastewater treatment.While various photobioreactors(PBRs)configurations have been widely applied for microalgae cultivation,limited research has focused on optimizing PBR design specificallyto enhance nitrogen and phosphorus removal efficiency.The high operational costs of wastewater treatment,combined with the inherent variability of microalgal growth,have prompted the search for advanced solutions that improve nitrogen and phosphorus removal while minimizing resource consumption and enabling predictive process control.Recently,the integration of PBR systems with artificialintelligence and machine learning(AI/ML)modeling has emerged as a transformative approach to enhancing nutrient removal,particularly for nitrogen and phosphorus.This study firstsummarizes existing PBR designs tailored for diverse applications,then outlines strategies for system enhancement through the optimization of mixing methods,construction materials,light intensity,and light source configuration.Furthermore,computational fluiddynamics(CFD)and AI/ML modeling are presented as tools to guide the structural design and operational optimization of microalgae-based nitrogen and phosphorus removal processes.Finally,future research directions and key challenges are discussed.展开更多
Artificial intelligence has the potential to stand as the cornerstone of human society,which could drive our civilization forward and emerge as a pivotal frontier in the ongoing technological revolution and industrial...Artificial intelligence has the potential to stand as the cornerstone of human society,which could drive our civilization forward and emerge as a pivotal frontier in the ongoing technological revolution and industrial transformation.Amidst profound shifts in the global technological landscape,smart materials,smart devices,and smart systems have become the defining pillars of our era,which will catalyze paradigm shifts in engineering science and reshape the trajectory of modern technology.展开更多
基金supported by the National Key Research and Development Program of China(No.2023YFC3011801)the Sprint Project of Chongqing Science and Health Joint Project(No.2025CCXM001)+1 种基金the General Project of Chongqing Science and Health Joint Project(No.2024MSXM084)the Science and Technology Research Program of Chongqing Municipal Education Commission(NO.KJQN202400613).
摘要Purpose:To develop and validate an artificialintelligence model based on focused assessment with sonography for trauma(FAST)for the semi-quantitative grading of intra-abdominal hemorrhage resulting from blunt abdominal trauma,particularly for use in prehospital or resource-limited settings.Methods:Nine Bama miniature pigs,mean weight(31.46±3.73)kg were enrolled.Graded hemorrhage from 0 to 1000 mL was simulated by infusing 100 mL of autologous arterial blood into the peritoneal cavity at each step.The hemorrhage volume was mapped to 3 grades based on total blood volume(estimated at 65 mL/kg):Grade Ⅰ(30%).FAST ultrasound videos were acquired from 6 standard sites:right upper quadrant-1,right upper quadrant-2,left upper quadrant-1,left upper quadrant-2,right pelvic cavity,and left pelvic cavity.The pixel area of hemorrhage was obtained by manually segmenting the frame with the largest fluidcollection using ITK-SNAP,and the corresponding scanning depth was recorded.A linear mixed-effects model was used to assess the impact of scanning depth on pixel area.A deep neural network,incorporating class weighting and dynamic probability threshold optimization,was constructed using a multimodal feature set including animal weight,pixel areas and scanning depths from each site,and the total pixel area.A 3-grade classificationwas performed.The model's performance was evaluated using leave-one-out cross-validation on an animal basis and compared with logistic regression,random forest,gradient boosting decision tree,and support vector machine.Results:A total of 797 raw videos were acquired,with 522 videos comprising 87 data groups(each covering 6 sites)included after screening.As hemorrhage volume increased,heart rate and shock index rose,while systolic blood pressure decreased;at 800 mL of hemorrhage,the shock index was 2.31±0.38.The mixed-effects model revealed a significantnegative correlation between scanning depth and pixel area(β=-2099.00,SE=1041.13,z=-2.02,p=0.044).The proposed model achieved an overall accuracy of 81.19%,outperforming support vector machine(73.77%),gradient boosting decision tree(70.63%),random forest(69.52%),and logistic regression(65.99%).Conclusion:In a porcine model of blunt abdominal trauma,a multimodal artificialintelligence approach based on FAST multi-site pixel area features,combined with a deep neural network optimized by class weighting and dynamic probability thresholds,can achieve semi-quantitative grading of intraabdominal hemorrhage.
摘要1.Introduction Scramjet is pivotal for achieving hypersonic flight,enabling vehicles to operate at speeds exceeding Mach number 5.This engine is crucial for next-generation aerospace systems,including hypersonic missiles,spaceplanes,and high-speed aircraft.However,the development of scramjet is fraught with significant technical challenges,such as supersonic combustion,thermal management,and dynamic flow control.
摘要The biological stabilization of soil using microbially induced carbonate precipitation(MICP)employs ureolytic bacteria to precipitate calcium carbonate(CaCO3),which binds soil particles,enhancing strength,stiffness,and erosion resistance.The unconfinedcompressive strength(UCS),a key measure of soil strength,is critical in geotechnical engineering as it directly reflectsthe mechanical stability of treated soils.This study integrates explainable artificialintelligence(XAI)with geotechnical insights to model the UCS of MICP-treated sands.Using 517 experimental data points and a combination of various input variables—including median grain size(D50),coefficientof uniformity(Cu),void ratio(e),urea concentration(Mu),calcium concentration(Mc),optical density(OD)of bacterial solution,pH,and total injection volume(Vt)—fivemachine learning(ML)models,including eXtreme gradient boosting(XGBoost),Light gradient boosting machine(LightGBM),random forest(RF),gene expression programming(GEP),and multivariate adaptive regression splines(MARS),were developed and optimized.The ensemble models(XGBoost,LightGBM,and RF)were optimized using the Chernobyl disaster optimizer(CDO),a recently developed metaheuristic algorithm.Of these,LightGBM-CDO achieved the highest accuracy for UCS prediction.XAI techniques like feature importance analysis(FIA),SHapley additive exPlanations(SHAP),and partial dependence plots(PDPs)were also used to investigate the complex non-linear relationships between the input and output variables.The results obtained have demonstrated that the XAI-driven models can enhance the predictive accuracy and interpretability of MICP processes,offering a sustainable pathway for optimizing geotechnical applications.
基金supported by the National Key R&D Program of China(Grant No.2024YFA1510302)Song Z and Qi Z also acknowledge support from the National Science Foundation of China(NSFC)under Grant Nos.22578115,22208098,and 22278134,respectively.
摘要1 Introduction Artificial intelligence(Al)has rapidly emerged as a transformative force across the chemical engineering field.From academia to industry,chemical engineers are leveraging data-driven models and advanced algorithms to optimize production,enhance safety,design novel processes and materials,and even generate new scientific insights.In recent years,the number of publications and projects applying machine learning(ML)and AI in process systems engineering(PSE),industrial data science,and chemical engineering more broadly has skyrocketed[1-3].
基金supported by the Ministry of Industry and Information Technology,China,the Science Foundation of the Ministry of Education of China(No.21YJC630072)the Key Talent Project of the Yan Zhao Golden Platform for Talent Attraction in Hebei Province,China(No.HJYB202528).
摘要Diverse energy and power systems have been playing a significantly critical role in the revolution of sustainable energy supply for the future,which have a great impact on energy resources and efficiencies.Due to the emerging artificial intelligence and machine learning,traditional modeling techniques in these energy systems have met challenges in still leveraging physics model and first principle-based approaches.Moreover,with the rapid development of hardware and computing techniques,new modeling approaches for energy systems have become more and more important for system design,integration,analysis,control,and management.
摘要The rapid advancement of artificial intelligence(AI)technologies,particularly the groundbreaking progress of large language models(LLMs)in the field of the natural language processing,has been profoundly reshaping the scientific research paradigms.
摘要The integration of artificial intelligence(AI)with biomedical optical imaging has emerged as one of the most transformative directions in modern biophotonics.From accelerating image reconstruction to enhancing quantitative analysis,AI-driven approaches are reshaping how we acquire,process,and interpret optical imaging data across scales—from subcellular structures to whole organisms.Deep learning,in particular,has demonstrated remarkable capacity to address long-standing challenges in computational imaging,including noise suppression,artifact correction,super-resolution reconstruction,and multi-modal data fusion.
摘要The conceptual framework for the hallmarks of cancer,which was first proposed by Hanahan and Weinberg in 20001 and updated in 20112 and 2022,3 with a more recent version published in the spring of 2026,is the foundational blueprint of modern cancer research.This latest review moves beyond a simple list of tumor traits to organize the immense complexity of cancer into four interconnected dimensions.4 The first dimension concerns acquired capabilities,which are the core functional capabilities cancer cells need to survive and spread.
摘要During the Two Sessions,members of the CPPCC National Committee and deputies to the NPC discussed issues of common concern in the standardization field,such as artificial intelligence(AI)and digital technologies,vehicles and new energy,construction engineering,as well as food and agricultural products.Here,we summarize their insights into standards,to help standards play a bigger role in vigorously promoting the Chinese modernization.
摘要As 2026 unfolds,the image of an autonomous port in Ningbo loading a U.S.-bound ship encapsulates the transformative power of China’s surge in artificial intelligence(AI).This automation marvel not only symbolizes China’s economic power but also demonstrates how deeply integrated AI has become into its global competition strategy.Once largely confined to academic research and pilot programs,AI is now embedded in China’s national strategy.The goal:drive productivity,modernize industries,and strengthen its competitive position in global technology markets.
摘要China Issues Three-year Plan to Boost AI Integration With Information,Communications Sector China’s Ministry of Industry and Information Technology recent1y re1eased a three-year p1an to accelerate the integration of artificial intelligence(AI)with the country's infor mation and communications sector,setting targets for more autonomous networks.
摘要Seventy years ago,a handful of young scholars gathered at Dartmouth College in New Hampshire and first uttered the words“artificial intelligence.”Seven decades later,as algorithms begin to“think”and machines step from the digital world into the physical one,the question is no longer whether AI will reshape human civilization,but who will write the score.
摘要主题群:AI与艺术篇幅:317词建议用时:6分钟.1 Reflecting on a favorite piece of art—whether a painting,song,novel or film—often brings about deeply personal connections rooted in emotion,meaning and human experience.Now,imagine that same work was generated by artificial intelligence.This situation is increasingly likely as AI rapidly evolves to produce works across creative fields like writing,visual art,music and choreography(编舞艺术).A recent survey sought to understand public views on this shift.
摘要Over 25 years ago,Jeanologia revolutionized the denim industry by introducing laser technology for jean finishing,a solution that replaced manual processes with high impact on both workers’health and the environment,marking the beginning of a new era in denim production.Today,the Spanish company is once again transforming the sector with the launch of BILLY,the first artificial intelligence developed specifically for the denim industry,capable of extracting precise designs directly from a picture.With this launch,Jeanologia brings AI into one of the most creative and complex phases of denim development:design.
摘要1 Artificial intelligence(AI)has become a debated creative tool in todays art world.When it comes to AI in art,it is essential to examine different types and uses separately.Generative AI,which creates animated digital artworks,deserves special attention.2 Using AI to create art raises important ethical questions that both creators and viewers must consider carefully.One major concern involves intellectual property—who owns the artwork created by AI systems,especially when these systems learn from existing copyrighted works?Another critical issue is bias in training data.If AI learns from biased information,the generated art may strengthen unfair ideas about certain groups or fail to represent them fairly.
摘要Trainers are shaping AI to respond with empathy,gentleness and emotional understanding “AI is my best friend,”24-yearold Yu Yang from the private training sector shared on social media.With its constant availability,efficiency and rationality,AI has become a true source of emotional support for certain users.
基金supported by the National Natural Science Foundation of China(Grant Nos.42472351 and 42177140)the Young Elite Scientist Sponsorship Program by the China Association for Science and Technology(Grant No.YESS20230742).
摘要In recent years,tunnel boring machines(TBMs)have been widely used in tunnel construction.Rockbursts,as a dynamic geological disaster,pose a serious threat to the safety and efficienttunneling of TBMs.The microseismic monitoring technique provides an effective solution for rockburst warning.However,due to the complexity and variability of the TBM excavation environment,microseismic events induced by rock fracture are often accompanied by interference events,such as electrical noise,TBM vibration,and mechanical knock.This study proposes a multi-channel intelligent classification approach for microseismic events in TBM excavation scenarios,based on double-layer stacking learning,to identify rock fractures.In this approach,decision tree is used as the base classifieron each microseismic channel,while extreme learning machine is employed as the meta-classifierto aggregate all base classifiers.Additionally,mind evolutionary computation is integrated to optimize the built-in hyperparameters of various classifiers.Meanwhile,a comprehensive preprocessing and augmentation flowfor microseismic data has been developed,encompassing feature extraction,dimensionality reduction,outlier detection,and outlier substitution.The results reveal that the multi-channel stacking model,which combines classificationand regression tree and extreme learning machine,achieves optimal global and local generalization performance compared to other multi-channel stacking models and traditional single-channel models.The accuracy,Hamming loss,and Cohen’s kappa are 96.75%,0.0325,and 0.9148,respectively,and the F1-score and AUC on rock fracture events are 0.9366 and 0.9818,respectively.Finally,a generative artificialintelligence-based scheme is invented to enhance the robustness of the model for signal-mixing events.
基金supported by the National Natural Science Foundation of China(62293500,62293502,and 62293504)the State Key Laboratory of Industrial Control Technology,China(ICT2024A22)the Programme of Introducing Talents of Discipline to Universities(the 111 Project)(B17017).
摘要1.Introduction Engineers,policymakers,and governments are currently facing the pressing global challenges of climate change and the energy crisis.To address the continuously increasing demand for energy and mitigate environmental damage,energy conservation and emissions reduction have become strategic priorities for sustainable development[1].Nations worldwide have reached a consensus on reducing carbon emissions and have introduced various policies and actions,such as the carbon peak and carbon neutrality targets proposed by China[2,3].
基金supported by the National Natural Science Foundation of China(22038012,U24A20543)the Science and Technology Pro-gram of Fujian Province,China(2025Y4001).
摘要The use of microalgae to recover nitrogen and phosphorus from wastewater has garnered significant attention,positioning it as one of the most promising and sustainable strategies in modern wastewater treatment.While various photobioreactors(PBRs)configurations have been widely applied for microalgae cultivation,limited research has focused on optimizing PBR design specificallyto enhance nitrogen and phosphorus removal efficiency.The high operational costs of wastewater treatment,combined with the inherent variability of microalgal growth,have prompted the search for advanced solutions that improve nitrogen and phosphorus removal while minimizing resource consumption and enabling predictive process control.Recently,the integration of PBR systems with artificialintelligence and machine learning(AI/ML)modeling has emerged as a transformative approach to enhancing nutrient removal,particularly for nitrogen and phosphorus.This study firstsummarizes existing PBR designs tailored for diverse applications,then outlines strategies for system enhancement through the optimization of mixing methods,construction materials,light intensity,and light source configuration.Furthermore,computational fluiddynamics(CFD)and AI/ML modeling are presented as tools to guide the structural design and operational optimization of microalgae-based nitrogen and phosphorus removal processes.Finally,future research directions and key challenges are discussed.
摘要Artificial intelligence has the potential to stand as the cornerstone of human society,which could drive our civilization forward and emerge as a pivotal frontier in the ongoing technological revolution and industrial transformation.Amidst profound shifts in the global technological landscape,smart materials,smart devices,and smart systems have become the defining pillars of our era,which will catalyze paradigm shifts in engineering science and reshape the trajectory of modern technology.