A simple but illustrative survey is given on various approaches of computational intelligence with their features, applications and the mathematical tools involved, among which the simulated annealing, neural networks...A simple but illustrative survey is given on various approaches of computational intelligence with their features, applications and the mathematical tools involved, among which the simulated annealing, neural networks, genetic and evolutionary programming, self-organizing learning and adapting algorithms, hidden Markov models are recommended intensively. The common mathematical features of various computational intelligence algorithms are exploited.Finally, two common principles of concessive strategies implicated in many computational intelligence algorithms are discussed.展开更多
Presented is a new testing system based on using the factor models and self-organizing feature maps as well as the method of filtering undesirable environment influence. Testing process is described by the factor mode...Presented is a new testing system based on using the factor models and self-organizing feature maps as well as the method of filtering undesirable environment influence. Testing process is described by the factor model with simplex structure, which represents the influences of genetics and environmental factors on the observed parameters - the answers to the questions of the test subjects in one case and for the time, which is spent on responding to each test question to another. The Monte Carlo method is applied to get sufficient samples for training self-organizing feature maps, which are used to estimate model goodness-of-fit measures and, consequently, ability level. A prototype of the system is implemented using the Raven＇s Progressive Matrices （Advanced Progressive Matrices） - an intelligence test of abstract reasoning. Elimination of environment influence results is performed by comparing the observed and predicted answers to the test tasks using the Kalman filter, which is adapted to solve the problem. The testing procedure is optimized by reducing the number of tasks using the distribution of measures to belong to different ability levels after performing each test task provided the required level of conclusion reliability is obtained.展开更多
Organic chemistry is undergoing a major paradigm shift,moving from a labor-intensive approach to a new era dominated by automation and artificial intelligence(AI).This transformative shift is being driven by technolog...Organic chemistry is undergoing a major paradigm shift,moving from a labor-intensive approach to a new era dominated by automation and artificial intelligence(AI).This transformative shift is being driven by technological advances,the ever-increasing demand for greater research efficiency and accuracy,and the burgeoning growth of interdisciplinary research.AI models,supported by computational power and algorithms,are drastically reshaping synthetic planning and introducing groundbreaking ways to tackle complex molecular synthesis.In addition,autonomous robotic systems are rapidly accelerating the pace of discovery by performing tedious tasks with unprecedented speed and precision.This article examines the multiple opportunities and challenges presented by this paradigm shift and explores its far-reaching implications.It provides valuable insights into the future trajectory of organic chemistry research,which is increasingly defined by the synergistic interaction of automation and AI.展开更多
Converting thermal energy into mechanical work by means of Organic Rankine Cycle is a validated technology to exploit low-grade waste heat.The typical design process of Organic Rankine Cycle system,which commonly in-v...Converting thermal energy into mechanical work by means of Organic Rankine Cycle is a validated technology to exploit low-grade waste heat.The typical design process of Organic Rankine Cycle system,which commonly in-volves working fluid selection,cycle configuration selection,operating parameters optimization,and component selection and sizing,is time-consuming and highly dependent on engineer’s experience.Thus,it is difficult to achieve the optimal design in most cases.In recent decades,artificial intelligence has been gradually introduced into the design of energy system to overcome above shortcomings.In order to clarify the research field of arti-ficial intelligence technique in Organic Rankine Cycle design and guide artificial intelligence technique to assist Organic Rankine Cycle design better,this study presents a preliminary literature summary on recent progresses of artificial intelligence technique in organic Rankine cycle systems design.First,this study analyzes four main procedures which constitute a typical design process of Organic Rankine Cycle systems and finds that design problems encountered during design process can be divided into three categories:decision making,parameter optimization and parameter prediction.In the second section,a detailed literature review on each design proce-dures using artificial intelligence algorithms is presented.At last,the state of art in this field and the prospects for the future work are provided.展开更多
Traditional synthesis made outstanding achievements but still suffers various drawbacks,such as manual operation,poor efficiency,and lack of reproducibility.Thanks to the development of laboratory automation,synthetic...Traditional synthesis made outstanding achievements but still suffers various drawbacks,such as manual operation,poor efficiency,and lack of reproducibility.Thanks to the development of laboratory automation,synthetic chemistry is now chasing a pavement from a labor-intensive process to intelligent automation.Herein,we highlight some of the most recent representative breakthroughs in automated synthesis and present an outlook for this field.We hope this Topic can arouse chemists'interest in automated synthe-sis and drive synthetic automation to a better intelligent and automatic way.展开更多
Polarimetry encompasses a collection of optical techniques broadly used in a variety of fields.Nowadays,such techniques have provided their suitability in the biomedical field through the study of the polarimetric res...Polarimetry encompasses a collection of optical techniques broadly used in a variety of fields.Nowadays,such techniques have provided their suitability in the biomedical field through the study of the polarimetric response of biological samples(retardance,dichroism and depolarization)by measuring certain polarimetric observables.One of these features,depolarization,is mainly produced by scattering on samples,which is a predominant efiect in turbid media as biological tissues.In turn,retardance and dichroic efiects are produced by tissue anisotropies and can lead to depolarization too.Since depolarization is a predominant efiect in tissue samples,we focus on studying difierent depolarization metrics for biomedical applications.We report the suitability of a set of depolarizing observables,the indices of polarimetric purity(IPPs),for biological tissue inspection.We review some results where we demonstrate that IPPs lead to better performance than the depolarization index,which is a well-established and commonly used depolarization observable in the literature.We also provide how IPPs are able to significantly enhance contrast between difierent tissue structures and even to reveal structures hidden by using standard intensity images.Finally,we also explore the classificatory potential of IPPs and other depolarizing observables for the discrimination of difierent tissues obtained from ex vivo chicken samples(muscle,tendon,myotendinous junction and bone),reaching accurate models for tissue classification.展开更多
Artificial intelligence(AI)is attractive due to its brain-like working pattern and efficient task processing.Light-stimulated synaptic devices show enormous potential in the field of neuromorphic computing.Here,we dev...Artificial intelligence(AI)is attractive due to its brain-like working pattern and efficient task processing.Light-stimulated synaptic devices show enormous potential in the field of neuromorphic computing.Here,we develop a kind of optical synaptic devices with a ternary photoactive material system consisting of organometal halide perovskite CHNH-PbBr,organic dye Rhodamine B(RhB),and organic semiconductor pentacene.We found that the introduction of RhB can significantly improve the light absorption and photoresponsivity of the composite devices.The devices exhibit acceptable synaptic behaviors and realize a brain-like learning pattern toward various input signals.Notably,the devices can respond to light signals with a low intensity of 1.1μW cm^(-2)and be operated at low working voltages.The devices achieve a low energy consumption of 1.25 fJ at a drain-source voltage of-50μV,comparable to that of a biological synaptic event.Moreover,the devices simulate a self-learning process,indicating their significantly improved learning efficiency.Also,the devices can recognize subtle differences in Morse codes,showing potential in the practical application of information encryption.The excellent optoelectronic performance demonstrates that the proposed ternary synaptic devices are advantageous in developing new AI.展开更多
文摘A simple but illustrative survey is given on various approaches of computational intelligence with their features, applications and the mathematical tools involved, among which the simulated annealing, neural networks, genetic and evolutionary programming, self-organizing learning and adapting algorithms, hidden Markov models are recommended intensively. The common mathematical features of various computational intelligence algorithms are exploited.Finally, two common principles of concessive strategies implicated in many computational intelligence algorithms are discussed.
文摘Presented is a new testing system based on using the factor models and self-organizing feature maps as well as the method of filtering undesirable environment influence. Testing process is described by the factor model with simplex structure, which represents the influences of genetics and environmental factors on the observed parameters - the answers to the questions of the test subjects in one case and for the time, which is spent on responding to each test question to another. The Monte Carlo method is applied to get sufficient samples for training self-organizing feature maps, which are used to estimate model goodness-of-fit measures and, consequently, ability level. A prototype of the system is implemented using the Raven＇s Progressive Matrices （Advanced Progressive Matrices） - an intelligence test of abstract reasoning. Elimination of environment influence results is performed by comparing the observed and predicted answers to the test tasks using the Kalman filter, which is adapted to solve the problem. The testing procedure is optimized by reducing the number of tasks using the distribution of measures to belong to different ability levels after performing each test task provided the required level of conclusion reliability is obtained.
基金supported by the National Natural Science Foundation of China(22071004,21933001 and 22150013)
文摘Organic chemistry is undergoing a major paradigm shift,moving from a labor-intensive approach to a new era dominated by automation and artificial intelligence(AI).This transformative shift is being driven by technological advances,the ever-increasing demand for greater research efficiency and accuracy,and the burgeoning growth of interdisciplinary research.AI models,supported by computational power and algorithms,are drastically reshaping synthetic planning and introducing groundbreaking ways to tackle complex molecular synthesis.In addition,autonomous robotic systems are rapidly accelerating the pace of discovery by performing tedious tasks with unprecedented speed and precision.This article examines the multiple opportunities and challenges presented by this paradigm shift and explores its far-reaching implications.It provides valuable insights into the future trajectory of organic chemistry research,which is increasingly defined by the synergistic interaction of automation and AI.
基金The work described in this paper was supported by the National Key Research and Development Plan under Grant No.2018YFB1501004.
文摘Converting thermal energy into mechanical work by means of Organic Rankine Cycle is a validated technology to exploit low-grade waste heat.The typical design process of Organic Rankine Cycle system,which commonly in-volves working fluid selection,cycle configuration selection,operating parameters optimization,and component selection and sizing,is time-consuming and highly dependent on engineer’s experience.Thus,it is difficult to achieve the optimal design in most cases.In recent decades,artificial intelligence has been gradually introduced into the design of energy system to overcome above shortcomings.In order to clarify the research field of arti-ficial intelligence technique in Organic Rankine Cycle design and guide artificial intelligence technique to assist Organic Rankine Cycle design better,this study presents a preliminary literature summary on recent progresses of artificial intelligence technique in organic Rankine cycle systems design.First,this study analyzes four main procedures which constitute a typical design process of Organic Rankine Cycle systems and finds that design problems encountered during design process can be divided into three categories:decision making,parameter optimization and parameter prediction.In the second section,a detailed literature review on each design proce-dures using artificial intelligence algorithms is presented.At last,the state of art in this field and the prospects for the future work are provided.
基金support from Guangzhou Laboratory,Bioland Laboratory,and the National Natural Science Foundation of China(22071249).
文摘Traditional synthesis made outstanding achievements but still suffers various drawbacks,such as manual operation,poor efficiency,and lack of reproducibility.Thanks to the development of laboratory automation,synthetic chemistry is now chasing a pavement from a labor-intensive process to intelligent automation.Herein,we highlight some of the most recent representative breakthroughs in automated synthesis and present an outlook for this field.We hope this Topic can arouse chemists'interest in automated synthe-sis and drive synthetic automation to a better intelligent and automatic way.
基金the financial support of Spanish MINECO(PID2021-126509OB-C21,and Fondos FEDER)Catalan Government(2017-SGR-001500).
文摘Polarimetry encompasses a collection of optical techniques broadly used in a variety of fields.Nowadays,such techniques have provided their suitability in the biomedical field through the study of the polarimetric response of biological samples(retardance,dichroism and depolarization)by measuring certain polarimetric observables.One of these features,depolarization,is mainly produced by scattering on samples,which is a predominant efiect in turbid media as biological tissues.In turn,retardance and dichroic efiects are produced by tissue anisotropies and can lead to depolarization too.Since depolarization is a predominant efiect in tissue samples,we focus on studying difierent depolarization metrics for biomedical applications.We report the suitability of a set of depolarizing observables,the indices of polarimetric purity(IPPs),for biological tissue inspection.We review some results where we demonstrate that IPPs lead to better performance than the depolarization index,which is a well-established and commonly used depolarization observable in the literature.We also provide how IPPs are able to significantly enhance contrast between difierent tissue structures and even to reveal structures hidden by using standard intensity images.Finally,we also explore the classificatory potential of IPPs and other depolarizing observables for the discrimination of difierent tissues obtained from ex vivo chicken samples(muscle,tendon,myotendinous junction and bone),reaching accurate models for tissue classification.
基金supported by the National Natural Science Foundation of China(62074111)the Science&Technology Foundation of Shanghai(20JC1415600 and 19JC1412402)+2 种基金Shanghai Municipal Science and Technology Major Project(2021SHZDZX0100)Shanghai Municipal Commission of Science and Technology Project(19511132101)the Fundamental Research Funds for the Central Universities。
文摘Artificial intelligence(AI)is attractive due to its brain-like working pattern and efficient task processing.Light-stimulated synaptic devices show enormous potential in the field of neuromorphic computing.Here,we develop a kind of optical synaptic devices with a ternary photoactive material system consisting of organometal halide perovskite CHNH-PbBr,organic dye Rhodamine B(RhB),and organic semiconductor pentacene.We found that the introduction of RhB can significantly improve the light absorption and photoresponsivity of the composite devices.The devices exhibit acceptable synaptic behaviors and realize a brain-like learning pattern toward various input signals.Notably,the devices can respond to light signals with a low intensity of 1.1μW cm^(-2)and be operated at low working voltages.The devices achieve a low energy consumption of 1.25 fJ at a drain-source voltage of-50μV,comparable to that of a biological synaptic event.Moreover,the devices simulate a self-learning process,indicating their significantly improved learning efficiency.Also,the devices can recognize subtle differences in Morse codes,showing potential in the practical application of information encryption.The excellent optoelectronic performance demonstrates that the proposed ternary synaptic devices are advantageous in developing new AI.
