In recent years,the country has spent significant workforce and material resources to prevent traffic accidents,particularly those caused by fatigued driving.The current studies mainly concentrate on driver physiologi...In recent years,the country has spent significant workforce and material resources to prevent traffic accidents,particularly those caused by fatigued driving.The current studies mainly concentrate on driver physiological signals,driving behavior,and vehicle information.However,most of the approaches are computationally intensive and inconvenient for real-time detection.Therefore,this paper designs a network that combines precision,speed and lightweight and proposes an algorithm for facial fatigue detection based on multi-feature fusion.Specifically,the face detection model takes YOLOv8(You Only Look Once version 8)as the basic framework,and replaces its backbone network with MobileNetv3.To focus on the significant regions in the image,CPCA(Channel Prior Convolution Attention)is adopted to enhance the network’s capacity for feature extraction.Meanwhile,the network training phase employs the Focal-EIOU(Focal and Efficient Intersection Over Union)loss function,which makes the network lightweight and increases the accuracy of target detection.Ultimately,the Dlib toolkit was employed to annotate 68 facial feature points.This study established an evaluation metric for facial fatigue and developed a novel fatigue detection algorithm to assess the driver’s condition.A series of comparative experiments were carried out on the self-built dataset.The suggested method’s mAP(mean Average Precision)values for object detection and fatigue detection are 96.71%and 95.75%,respectively,as well as the detection speed is 47 FPS(Frames Per Second).This method can balance the contradiction between computational complexity and model accuracy.Furthermore,it can be transplanted to NVIDIA Jetson Orin NX and quickly detect the driver’s state while maintaining a high degree of accuracy.It contributes to the development of automobile safety systems and reduces the occurrence of traffic accidents.展开更多
Previous studies aiming to accelerate data processing have focused on enhancement algorithms,using the graphics processing unit(GPU)to speed up programs,and thread-level parallelism.These methods overlook maximizing t...Previous studies aiming to accelerate data processing have focused on enhancement algorithms,using the graphics processing unit(GPU)to speed up programs,and thread-level parallelism.These methods overlook maximizing the utilization of existing central processing unit(CPU)resources and reducing human and computational time costs via process automation.Accordingly,this paper proposes a scheme,called SSM,that combines“Srun job submission mode”,“Sbatch job submission mode”,and“Monitor function”.The SSM scheme includes three main modules:data management,command management,and resource management.Its core innovations are command splitting and parallel execution.The results show that this method effectively improves CPU utilization and reduces the time required for data processing.In terms of CPU utilization,the average value of this scheme is 89%.In contrast,the average CPU utilizations of“Srun job submission mode”and“Sbatch job submission mode”are significantly lower,at 43%and 52%,respectively.In terms of the data-processing time,SSM testing on the Five-hundred-meter Aperture Spherical radio Telescope(FAST)data requires only 5.5 h,compared with 8 h in the“Srun job submission mode”and 14 h in the“Sbatch job submission mode”.In addition,tests on the FAST and Parkes datasets demonstrate the universality of the SSM scheme,which can process data from different telescopes.The compatibility of the SSM scheme for pulsar searches is verified using 2 days of observational data from the globular cluster M2,with the scheme successfully discovering all published pulsars in M2.展开更多
The Multipurpose Enhanced Cognitive Architecture(MECA)is a cognitive framework designed to model complex,human-like processes across multiple domains.Originally focusing on implementing a Dual Process Theory approach ...The Multipurpose Enhanced Cognitive Architecture(MECA)is a cognitive framework designed to model complex,human-like processes across multiple domains.Originally focusing on implementing a Dual Process Theory approach and integrating a machine consciousness mechanism based on Global Workspace Theory,MECA has been updated to integrate a dual-layer subsumption mechanism,enabling both reactive and deliberative behaviors,dynamic goal setting and a visual-spatial memory subsystem,enhancing MECA’s capacity for real-world interaction and adaptive behavior.Also,with the introduction of the new computational ideas’knowledge representation scheme,MECA proposes to organize knowledge dynamically to handle context-sensitive reasoning and flexible categorization.MECA’s implementation relies on the Cognitive Systems Toolkit(CST),facilitating its integration with cutting-edge technologies.MECA and CST are being continuously developed and updated,aligned,and open to incorporate the latest AI artifacts and methodologies.This approach ensures the delivery of organized,monitorable,auditable,and controllable AI solutions,significantly reducing reliance on“black box”cognitive processes while enhancing transparency and accountability in AI-driven systems.These updates reinforce MECA’s potential as a robust architecture for developing autonomous,adaptable,and context-aware AI systems capable of real-world interaction and adaptive learning.展开更多
Searching and designing new materials play crucial roles in the development of energy storage devices. In today's world where machine learning technology has shown strong predictive ability for various tasks, the ...Searching and designing new materials play crucial roles in the development of energy storage devices. In today's world where machine learning technology has shown strong predictive ability for various tasks, the combination with machine learning technology will accelerate the process of material development. Herein, we develop ESM Cloud Toolkit for energy storage materials based on Mat Elab platform, which is designed as a convenient and accurate way to automatically record and save the raw data of scientific research. The ESM Cloud Toolkit includes multiple features such as automatic archiving of computational simulation data, post-processing of experimental data, and machine learning applications. It makes the entire research workflow more automated and reduces the entry barrier for the application of machine learning technology in the domain of energy storage materials. It integrates data archive, traceability, processing, and reutilization, and allows individual research data to play a greater role in the era of AI.展开更多
Alfalfa(Medicago sativa.L.)is a globally significant autotetraploid legume forage crop.However,despite its importance,establishing efficient gene editing systems for cultivated alfalfa remains a formidable challenge.I...Alfalfa(Medicago sativa.L.)is a globally significant autotetraploid legume forage crop.However,despite its importance,establishing efficient gene editing systems for cultivated alfalfa remains a formidable challenge.In this study,we pioneered the development of a highly effective ultrasonic-assisted leaf disc transformation system for Gongnong 1 alfalfa,a variety widely cultivated in Northeast China.Subsequently,we created a single transcript CRISPR/Cas9(CRISPR_2.0)toolkit,incorporating multiplex gRNAs,designed for gene editing in Gongnong 1.Both Cas9 and gRNA scaffolds were under the control of the Arabidopsis ubiquitin-10 promoter,a widely employed polymeraseⅡconstitutive promoter known for strong transgene expression in dicots.To assess the toolkit’s efficiency,we targeted PALM1,a gene associated with a recognizable multifoliate phenotype.Utilizing the CRISPR_2.0 toolkit,we directed PALM1 editing at two sites in the wild-type Gongnong 1.Results indicated a 35.1%occurrence of editing events all in target 2 alleles,while no mutations were detected at target 1 in the transgenic-positive lines.To explore more efficient sgRNAs,we developed a rapid,reliable screening system based on Agrobacterium rhizogenes-mediated hairy root transformation,incorporating the visible reporter MtLAP1.This screening system demonstrated that most purple visible hairy roots underwent gene editing.Notably,sgRNA3,with an 83.0%editing efficiency,was selected using the visible hairy root system.As anticipated,tetra-allelic homozygous palm1 mutations exhibited a clear multifoliate phenotype.These palm1 lines demonstrated an average crude protein yield increase of 21.5%compared to trifoliolate alfalfa.Our findings highlight the modified CRISPR_2.0 system as a highly efficient and robust gene editing tool for autotetraploid alfalfa.展开更多
基金supported by the Science and Technology Bureau of Xi’an project(24KGDW0049)the Key Research and Development Programof Shaanxi(2023-YBGY-264)the Key Research and Development Program of Guangxi(GK-AB20159032).
文摘In recent years,the country has spent significant workforce and material resources to prevent traffic accidents,particularly those caused by fatigued driving.The current studies mainly concentrate on driver physiological signals,driving behavior,and vehicle information.However,most of the approaches are computationally intensive and inconvenient for real-time detection.Therefore,this paper designs a network that combines precision,speed and lightweight and proposes an algorithm for facial fatigue detection based on multi-feature fusion.Specifically,the face detection model takes YOLOv8(You Only Look Once version 8)as the basic framework,and replaces its backbone network with MobileNetv3.To focus on the significant regions in the image,CPCA(Channel Prior Convolution Attention)is adopted to enhance the network’s capacity for feature extraction.Meanwhile,the network training phase employs the Focal-EIOU(Focal and Efficient Intersection Over Union)loss function,which makes the network lightweight and increases the accuracy of target detection.Ultimately,the Dlib toolkit was employed to annotate 68 facial feature points.This study established an evaluation metric for facial fatigue and developed a novel fatigue detection algorithm to assess the driver’s condition.A series of comparative experiments were carried out on the self-built dataset.The suggested method’s mAP(mean Average Precision)values for object detection and fatigue detection are 96.71%and 95.75%,respectively,as well as the detection speed is 47 FPS(Frames Per Second).This method can balance the contradiction between computational complexity and model accuracy.Furthermore,it can be transplanted to NVIDIA Jetson Orin NX and quickly detect the driver’s state while maintaining a high degree of accuracy.It contributes to the development of automobile safety systems and reduces the occurrence of traffic accidents.
基金supported by the National Nature Science Foundation of China(12363010)supported by the Guizhou Provincial Basic Research Program(Natural Science)(ZK[2023]039)the Key Technology R&D Program([2023]352).
文摘Previous studies aiming to accelerate data processing have focused on enhancement algorithms,using the graphics processing unit(GPU)to speed up programs,and thread-level parallelism.These methods overlook maximizing the utilization of existing central processing unit(CPU)resources and reducing human and computational time costs via process automation.Accordingly,this paper proposes a scheme,called SSM,that combines“Srun job submission mode”,“Sbatch job submission mode”,and“Monitor function”.The SSM scheme includes three main modules:data management,command management,and resource management.Its core innovations are command splitting and parallel execution.The results show that this method effectively improves CPU utilization and reduces the time required for data processing.In terms of CPU utilization,the average value of this scheme is 89%.In contrast,the average CPU utilizations of“Srun job submission mode”and“Sbatch job submission mode”are significantly lower,at 43%and 52%,respectively.In terms of the data-processing time,SSM testing on the Five-hundred-meter Aperture Spherical radio Telescope(FAST)data requires only 5.5 h,compared with 8 h in the“Srun job submission mode”and 14 h in the“Sbatch job submission mode”.In addition,tests on the FAST and Parkes datasets demonstrate the universality of the SSM scheme,which can process data from different telescopes.The compatibility of the SSM scheme for pulsar searches is verified using 2 days of observational data from the globular cluster M2,with the scheme successfully discovering all published pulsars in M2.
基金Supported by the Sao Paulo Research Foundation(FAPESP),CPE SMARTNESS(2021/00199-8)and CEPID/BRAINN(2013/07559-3).
文摘The Multipurpose Enhanced Cognitive Architecture(MECA)is a cognitive framework designed to model complex,human-like processes across multiple domains.Originally focusing on implementing a Dual Process Theory approach and integrating a machine consciousness mechanism based on Global Workspace Theory,MECA has been updated to integrate a dual-layer subsumption mechanism,enabling both reactive and deliberative behaviors,dynamic goal setting and a visual-spatial memory subsystem,enhancing MECA’s capacity for real-world interaction and adaptive behavior.Also,with the introduction of the new computational ideas’knowledge representation scheme,MECA proposes to organize knowledge dynamically to handle context-sensitive reasoning and flexible categorization.MECA’s implementation relies on the Cognitive Systems Toolkit(CST),facilitating its integration with cutting-edge technologies.MECA and CST are being continuously developed and updated,aligned,and open to incorporate the latest AI artifacts and methodologies.This approach ensures the delivery of organized,monitorable,auditable,and controllable AI solutions,significantly reducing reliance on“black box”cognitive processes while enhancing transparency and accountability in AI-driven systems.These updates reinforce MECA’s potential as a robust architecture for developing autonomous,adaptable,and context-aware AI systems capable of real-world interaction and adaptive learning.
基金supported by the National Natural Science Foundation of China (Grant Nos. 52022106 and 52172258)the Informatization Plan of Chinese Academy of Sciences (Grant No. CASWX2021SF-0102)。
文摘Searching and designing new materials play crucial roles in the development of energy storage devices. In today's world where machine learning technology has shown strong predictive ability for various tasks, the combination with machine learning technology will accelerate the process of material development. Herein, we develop ESM Cloud Toolkit for energy storage materials based on Mat Elab platform, which is designed as a convenient and accurate way to automatically record and save the raw data of scientific research. The ESM Cloud Toolkit includes multiple features such as automatic archiving of computational simulation data, post-processing of experimental data, and machine learning applications. It makes the entire research workflow more automated and reduces the entry barrier for the application of machine learning technology in the domain of energy storage materials. It integrates data archive, traceability, processing, and reutilization, and allows individual research data to play a greater role in the era of AI.
基金supported by the Strategic Priority Research Program of the Chinese Academy of Sciences(XDA26030301)Hohhot Key R&D Project(2023-JBGSS-1),the National Natural Science Foundation of China(U23A200206,32071864,32325035)+1 种基金the Taishan Scholar Program of Shandong(to Chunxiang Fu)the Shandong Provincial Natural Science Foundation(ZR202210270038)。
文摘Alfalfa(Medicago sativa.L.)is a globally significant autotetraploid legume forage crop.However,despite its importance,establishing efficient gene editing systems for cultivated alfalfa remains a formidable challenge.In this study,we pioneered the development of a highly effective ultrasonic-assisted leaf disc transformation system for Gongnong 1 alfalfa,a variety widely cultivated in Northeast China.Subsequently,we created a single transcript CRISPR/Cas9(CRISPR_2.0)toolkit,incorporating multiplex gRNAs,designed for gene editing in Gongnong 1.Both Cas9 and gRNA scaffolds were under the control of the Arabidopsis ubiquitin-10 promoter,a widely employed polymeraseⅡconstitutive promoter known for strong transgene expression in dicots.To assess the toolkit’s efficiency,we targeted PALM1,a gene associated with a recognizable multifoliate phenotype.Utilizing the CRISPR_2.0 toolkit,we directed PALM1 editing at two sites in the wild-type Gongnong 1.Results indicated a 35.1%occurrence of editing events all in target 2 alleles,while no mutations were detected at target 1 in the transgenic-positive lines.To explore more efficient sgRNAs,we developed a rapid,reliable screening system based on Agrobacterium rhizogenes-mediated hairy root transformation,incorporating the visible reporter MtLAP1.This screening system demonstrated that most purple visible hairy roots underwent gene editing.Notably,sgRNA3,with an 83.0%editing efficiency,was selected using the visible hairy root system.As anticipated,tetra-allelic homozygous palm1 mutations exhibited a clear multifoliate phenotype.These palm1 lines demonstrated an average crude protein yield increase of 21.5%compared to trifoliolate alfalfa.Our findings highlight the modified CRISPR_2.0 system as a highly efficient and robust gene editing tool for autotetraploid alfalfa.
