Numerous studies have shown abnormal brain functional connectivity in individuals with Alzheimer’s disease(AD)or amnestic mild cognitive impairment(aMCI).However,most studies examined traditional resting state functi...Numerous studies have shown abnormal brain functional connectivity in individuals with Alzheimer’s disease(AD)or amnestic mild cognitive impairment(aMCI).However,most studies examined traditional resting state functional connections,ignoring the instantaneous connection mode of the whole brain.In this case-control study,we used a new method called dynamic functional connectivity(DFC)to look for abnormalities in patients with AD and aMCI.We calculated dynamic functional connectivity strength from functional magnetic resonance imaging data for each participant,and then used a support vector machine to classify AD patients and normal controls.Finally,we highlighted brain regions and brain networks that made the largest contributions to the classification.We found differences in dynamic function connectivity strength in the left precuneus,default mode network,and dorsal attention network among normal controls,aMCI patients,and AD patients.These abnormalities are potential imaging markers for the early diagnosis of AD.展开更多
Oxygen reduction reaction(ORR)and oxygen evolution reaction(OER)are key catalytic processes in various renewable energy conversion and energy storage technologies.Herein,we systematically investigated the ORR and OER ...Oxygen reduction reaction(ORR)and oxygen evolution reaction(OER)are key catalytic processes in various renewable energy conversion and energy storage technologies.Herein,we systematically investigated the ORR and OER catalytic activity of the single-atom catalysts(SACs)composed of 4d/5d period transition metal(TM)atoms embedded on MBene substrates(TM-M_(2)B_(2)O_(2),M=Ti,Mo,and W).We found that TM dominates the catalytic activity compared to the MBene substrates.The SACs embedded with Rh,Pd,Au,and Ir exhibit excellent ORR or OER catalytic activity.Specifically,Rh-Mo2B2O2and Rh-W2B2O2are promising bifunctional catalysts with ultra-low ORR/OER overpotentials of 0.39/0.21 V and0.19/0.32 V,respectively,lower than that of Pt/RuO_(2)(0.45/0.42 V).Importantly,through machine learning,the models containing 10 element features of SACs were developed to quickly and accurately identify the superior ORR and OER electrocatalysts.Our findings provide several promising SACs for ORR and OER,and offer effective models for catalyst design.展开更多
The machine learning models of multiple linear regression(MLR),support vector regression(SVR),and extreme learning ma-chine(ELM)and the proposed ELM models of online sequential ELM(OS-ELM)and OS-ELM with forgetting me...The machine learning models of multiple linear regression(MLR),support vector regression(SVR),and extreme learning ma-chine(ELM)and the proposed ELM models of online sequential ELM(OS-ELM)and OS-ELM with forgetting mechanism(FOS-ELM)are applied in the prediction of the lime utilization ratio of dephosphorization in the basic oxygen furnace steelmaking process.The ELM model exhibites the best performance compared with the models of MLR and SVR.OS-ELM and FOS-ELM are applied for sequential learning and model updating.The optimal number of samples in validity term of the FOS-ELM model is determined to be 1500,with the smallest population mean absolute relative error(MARE)value of 0.058226 for the population.The variable importance analysis reveals lime weight,initial P content,and hot metal weight as the most important variables for the lime utilization ratio.The lime utilization ratio increases with the decrease in lime weight and the increases in the initial P content and hot metal weight.A prediction system based on FOS-ELM is applied in actual industrial production for one month.The hit ratios of the predicted lime utilization ratio in the error ranges of±1%,±3%,and±5%are 61.16%,90.63%,and 94.11%,respectively.The coefficient of determination,MARE,and root mean square error are 0.8670,0.06823,and 1.4265,respectively.The system exhibits desirable performance for applications in actual industrial pro-duction.展开更多
The revolutionary development of machine learning(ML),data science,and analytics,coupled with its application in material science,stands as a significant milestone of the scientific community over the last decade.Inve...The revolutionary development of machine learning(ML),data science,and analytics,coupled with its application in material science,stands as a significant milestone of the scientific community over the last decade.Investigating active,stable,and cost-efficient catalysts is crucial for oxygen evolution reaction owing to the significance in a range of electrochemical energy co nversion processes.In this work,we have demonstrated an efficient approach of high-throughput screening to find stable transition metal oxides under acid condition for high-performance oxygen evolution reaction(OER)catalysts through density functional theory(DFT)calculation and a machine learning algorithm.A methodology utilizing both the Materials Project database and DFT calculations was introduced to assess the acid stability under specific reaction conditions.Building upon this,OER catalytic activity of acid-stable materials was examined,highlighting potential OER catalysts that meet the required properties.We identified IrO_(2),Fe(SbO_(3))_(2),Co(SbO_(3))_(2),Ni(SbO_(3))_(2),FeSbO_(4),Fe(SbO_(3))4,MoWO_(6),TiSnO_(4),CoSbO_(4),and Ti(WO_(4))_(2)as promising catalysts,several of which have already been experimentally discovered for their robust OER performance,while others are novel for experimental exploration,thereby broadening the chemical scope for efficient OER electrocatalysts.Descriptors of the bond length of TM-O and the first ionization energy were used to unveil the OER activity origin.From the calculated results,guidance has been derived to effectively execute advanced high-throughput screenings for the discovery of catalysts with favorable properties.Furthermore,the intrinsic correlation between catalytic performance and various atomic and structural factors was elucidated using the ML algorithm.Through these approaches,we not only streamline the choice of the promising electrocatalysts but also offer insights for the design of varied catalyst models and the discovery of superior catalysts.展开更多
Electrochemical reactions are essential in the processes of energy storage and conversion,and performance is tightly dependent on the electrocatalysts.Herein,we systematically investigate the activity of 3d transition...Electrochemical reactions are essential in the processes of energy storage and conversion,and performance is tightly dependent on the electrocatalysts.Herein,we systematically investigate the activity of 3d transition metal embedded nitrogen-doped graphene(MN_(x)-G)for single-atom catalysts(SACs)in the oxygen reduction reaction(ORR),oxygen evolution reaction(OER),and hydrogen evolution reaction(HER).The calculated volcano curves reveal the optimal SAC configuration for each reaction to be CoN_(3)-G for the ORR,CoN_(4)-G for the OER,and Ni/CuN_(3)-G for the HER.Analysis based on the machine learning method suggests that high catalytic performance is dominated by the number of valence electrons occupying the d orbitals,the covalent radius,the electronegativity,the ratio of nearest-neighbor N and C atoms for the metal atoms,and the bond length between metal atoms and adsorbates.This work may shed some light on further studies of the ORR,OER,and HER with non-precious metal SACs.展开更多
There is an urgent need to develop efficient evaluation tools that use easily measured variables to make rapid and timely eutrophication assessments, which are important for marine health management, and to implement ...There is an urgent need to develop efficient evaluation tools that use easily measured variables to make rapid and timely eutrophication assessments, which are important for marine health management, and to implement eutrophication monitoring programs. In this study, an approach for rapidly assessing the eutrophication status of coastal waters with three easily measured parameters （turbidity, chlorophyll a and dissolved oxygen） was developed by the grid search （GS） optimized support vector machine （SVM）, with trophic index TRIX classification results as the reference. With the optimized penalty parameter C=64 and the kernel parameter y=l, the classification accuracy rates reached 89.3% for the training data, 88.3% for the cross-validation, and 88.5% for the validation dataset. Because the developed approach only used three easy-to-measure variables, its application could facilitate the rapid assessment of the eutrophication status of coastal waters, resulting in potential cost savings in marine monitoring programs and assisting in the provision of timely advice for marine management.展开更多
基金supported by the National Natural Science Foundation of China,No.81471120Fund Projects in Technology of the Foundation Strengthening Program of China,No.2019-JCJQ-JJ-151(both to XZ).
文摘Numerous studies have shown abnormal brain functional connectivity in individuals with Alzheimer’s disease(AD)or amnestic mild cognitive impairment(aMCI).However,most studies examined traditional resting state functional connections,ignoring the instantaneous connection mode of the whole brain.In this case-control study,we used a new method called dynamic functional connectivity(DFC)to look for abnormalities in patients with AD and aMCI.We calculated dynamic functional connectivity strength from functional magnetic resonance imaging data for each participant,and then used a support vector machine to classify AD patients and normal controls.Finally,we highlighted brain regions and brain networks that made the largest contributions to the classification.We found differences in dynamic function connectivity strength in the left precuneus,default mode network,and dorsal attention network among normal controls,aMCI patients,and AD patients.These abnormalities are potential imaging markers for the early diagnosis of AD.
基金supported by the National Key Research and Development Program of China(2022YFB3807200)
文摘Oxygen reduction reaction(ORR)and oxygen evolution reaction(OER)are key catalytic processes in various renewable energy conversion and energy storage technologies.Herein,we systematically investigated the ORR and OER catalytic activity of the single-atom catalysts(SACs)composed of 4d/5d period transition metal(TM)atoms embedded on MBene substrates(TM-M_(2)B_(2)O_(2),M=Ti,Mo,and W).We found that TM dominates the catalytic activity compared to the MBene substrates.The SACs embedded with Rh,Pd,Au,and Ir exhibit excellent ORR or OER catalytic activity.Specifically,Rh-Mo2B2O2and Rh-W2B2O2are promising bifunctional catalysts with ultra-low ORR/OER overpotentials of 0.39/0.21 V and0.19/0.32 V,respectively,lower than that of Pt/RuO_(2)(0.45/0.42 V).Importantly,through machine learning,the models containing 10 element features of SACs were developed to quickly and accurately identify the superior ORR and OER electrocatalysts.Our findings provide several promising SACs for ORR and OER,and offer effective models for catalyst design.
基金supported by the National Natural Science Foundation of China (No.U1960202).
文摘The machine learning models of multiple linear regression(MLR),support vector regression(SVR),and extreme learning ma-chine(ELM)and the proposed ELM models of online sequential ELM(OS-ELM)and OS-ELM with forgetting mechanism(FOS-ELM)are applied in the prediction of the lime utilization ratio of dephosphorization in the basic oxygen furnace steelmaking process.The ELM model exhibites the best performance compared with the models of MLR and SVR.OS-ELM and FOS-ELM are applied for sequential learning and model updating.The optimal number of samples in validity term of the FOS-ELM model is determined to be 1500,with the smallest population mean absolute relative error(MARE)value of 0.058226 for the population.The variable importance analysis reveals lime weight,initial P content,and hot metal weight as the most important variables for the lime utilization ratio.The lime utilization ratio increases with the decrease in lime weight and the increases in the initial P content and hot metal weight.A prediction system based on FOS-ELM is applied in actual industrial production for one month.The hit ratios of the predicted lime utilization ratio in the error ranges of±1%,±3%,and±5%are 61.16%,90.63%,and 94.11%,respectively.The coefficient of determination,MARE,and root mean square error are 0.8670,0.06823,and 1.4265,respectively.The system exhibits desirable performance for applications in actual industrial pro-duction.
基金supported by the Soonchunhyang University Research Fundsupported by the Supercomputing Center/Korea Institute of Science and Technology Information with supercomputing resources(KSC-2022-CRE-0354)+5 种基金supported by the “Regional Innovation Strategy(RIS)”through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(MOE)(2021RIS-004)a study on the“Leaders in INdustry-university Cooperation 3.0”Project,supported by the Ministry of Education and National Research Foundation of Koreafunded by BK 21 FOUR(Fostering Outstanding Universities for Research)(5199991614564)supported by the National Research Council of Science&Technology(NST)grant by the Korea government(MSIT)(CRC-20-01-NFRI)supported by the research fund of Hanyang University(HY-2022-3095)supported by the Technology Innovation Program(20023140,Development of an integrated low-power,highperformance,cryogenic high-vacuum exhaust system for analyzing impurity concentrations in the process in real time)funded By the Ministry of Trade,Industry&Energy(MOTIE,Korea)。
文摘The revolutionary development of machine learning(ML),data science,and analytics,coupled with its application in material science,stands as a significant milestone of the scientific community over the last decade.Investigating active,stable,and cost-efficient catalysts is crucial for oxygen evolution reaction owing to the significance in a range of electrochemical energy co nversion processes.In this work,we have demonstrated an efficient approach of high-throughput screening to find stable transition metal oxides under acid condition for high-performance oxygen evolution reaction(OER)catalysts through density functional theory(DFT)calculation and a machine learning algorithm.A methodology utilizing both the Materials Project database and DFT calculations was introduced to assess the acid stability under specific reaction conditions.Building upon this,OER catalytic activity of acid-stable materials was examined,highlighting potential OER catalysts that meet the required properties.We identified IrO_(2),Fe(SbO_(3))_(2),Co(SbO_(3))_(2),Ni(SbO_(3))_(2),FeSbO_(4),Fe(SbO_(3))4,MoWO_(6),TiSnO_(4),CoSbO_(4),and Ti(WO_(4))_(2)as promising catalysts,several of which have already been experimentally discovered for their robust OER performance,while others are novel for experimental exploration,thereby broadening the chemical scope for efficient OER electrocatalysts.Descriptors of the bond length of TM-O and the first ionization energy were used to unveil the OER activity origin.From the calculated results,guidance has been derived to effectively execute advanced high-throughput screenings for the discovery of catalysts with favorable properties.Furthermore,the intrinsic correlation between catalytic performance and various atomic and structural factors was elucidated using the ML algorithm.Through these approaches,we not only streamline the choice of the promising electrocatalysts but also offer insights for the design of varied catalyst models and the discovery of superior catalysts.
基金supported by the National Natural Science Foundation of China(No.21933006,21773124)the Fundamental Research Funds for the Central Universities Nankai University(No.63213042)the Supercomputing Center of Nankai University(NKSC).
文摘Electrochemical reactions are essential in the processes of energy storage and conversion,and performance is tightly dependent on the electrocatalysts.Herein,we systematically investigate the activity of 3d transition metal embedded nitrogen-doped graphene(MN_(x)-G)for single-atom catalysts(SACs)in the oxygen reduction reaction(ORR),oxygen evolution reaction(OER),and hydrogen evolution reaction(HER).The calculated volcano curves reveal the optimal SAC configuration for each reaction to be CoN_(3)-G for the ORR,CoN_(4)-G for the OER,and Ni/CuN_(3)-G for the HER.Analysis based on the machine learning method suggests that high catalytic performance is dominated by the number of valence electrons occupying the d orbitals,the covalent radius,the electronegativity,the ratio of nearest-neighbor N and C atoms for the metal atoms,and the bond length between metal atoms and adsorbates.This work may shed some light on further studies of the ORR,OER,and HER with non-precious metal SACs.
基金Supported by the National Key Research and Development Program(No.2016YFC1402101)the National Natural Science Foundation of China(No.41376106)the Natural Science Foundation of Shandong Province(No.ZR2013DM017)
文摘There is an urgent need to develop efficient evaluation tools that use easily measured variables to make rapid and timely eutrophication assessments, which are important for marine health management, and to implement eutrophication monitoring programs. In this study, an approach for rapidly assessing the eutrophication status of coastal waters with three easily measured parameters （turbidity, chlorophyll a and dissolved oxygen） was developed by the grid search （GS） optimized support vector machine （SVM）, with trophic index TRIX classification results as the reference. With the optimized penalty parameter C=64 and the kernel parameter y=l, the classification accuracy rates reached 89.3% for the training data, 88.3% for the cross-validation, and 88.5% for the validation dataset. Because the developed approach only used three easy-to-measure variables, its application could facilitate the rapid assessment of the eutrophication status of coastal waters, resulting in potential cost savings in marine monitoring programs and assisting in the provision of timely advice for marine management.
