Geo-engineering problems are known for their complexity and high uncertainty levels,requiring precise defini-tions,past experiences,logical reasoning,mathematical analysis,and practical insight to address them effecti...Geo-engineering problems are known for their complexity and high uncertainty levels,requiring precise defini-tions,past experiences,logical reasoning,mathematical analysis,and practical insight to address them effectively.Soft Computing(SC)methods have gained popularity in engineering disciplines such as mining and civil engineering due to computer hardware and machine learning advancements.Unlike traditional hard computing approaches,SC models use soft values and fuzzy sets to navigate uncertain environments.This study focuses on the application of SC methods to predict backbreak,a common issue in blasting operations within mining and civil projects.Backbreak,which refers to the unintended fracturing of rock beyond the desired blast perimeter,can significantly impact project timelines and costs.This study aims to explore how SC methods can be effectively employed to anticipate and mitigate the undesirable consequences of blasting operations,specifically focusing on backbreak prediction.The research explores the complexities of backbreak prediction and highlights the potential benefits of utilizing SC methods to address this challenging issue in geo-engineering projects.展开更多
Rock slope along motorways in the Higher Himalayan terrains are prone to various types of failure.In order to effectively mitigate these failures,a thorough assessment of rock mass behavior is entailed.The present res...Rock slope along motorways in the Higher Himalayan terrains are prone to various types of failure.In order to effectively mitigate these failures,a thorough assessment of rock mass behavior is entailed.The present research employs and compares widely practiced geo-mechanical classification schemes viz.,RQD,RMR,SMR,Q-slope,and GSI.A 23 km road cut section,along Sangla to Chitkul route,in Higher Himalayan region(India)has been taken up for this work.Total of 18 locations were selected,and their slope and rockmass properties were examined.Afterwards,the most influencing parameters in RMR,SMR,and Q-Slope were evaluated through a machine learning algorithm,i.e.,Random Forest.For RMRbasic,about 83%of rock-slopes were designated in good condition and rest were of Fair quality.Evaluation of slope mass rating along all 18-locations highlighted eight-sites as partially unstable,six-sites as partially stable.Remaining four locations varied between,Very Bad to Bad slope-conditions,necessitating the installation of mechanical supports and redesign of slopes.For SMR classification,feature importance analysis revealed the predominance of F3 variable,RQD and intact rock strength.Q-Slope approach was incorporated to identify the most stable steepest angle of the examined locations.For Q-Slope rating,Jn and RQD were found to have the most influence in classification of the slopes.Three zones on the basis of GSI-scores have been identified in the study area,i.e.,A(6595),B(4555),and C(2535).This study highlights the application of multiple geomechanical classification schemes,demonstrating how each approach can complement the others.展开更多
The distribution networks sometimes suffer from excessive losses and voltage violations in densely populated areas. The aim of the present study is to improve the performance of a distribution network by successively ...The distribution networks sometimes suffer from excessive losses and voltage violations in densely populated areas. The aim of the present study is to improve the performance of a distribution network by successively applying mono-capacitor positioning, multiple positioning and reconfiguration processes using GA-based algorithms implemented in a Matlab environment. From the diagnostic study of this network, it was observed that a minimum voltage of 0.90 pu induces a voltage deviation of 5.26%, followed by active and reactive losses of 425.08 kW and 435.09 kVAR, respectively. Single placement with the NSGAII resulted in the placement of a 3000 kVAR capacitor at node 128, which proved to be the invariably neuralgic point. Multiple placements resulted in a 21.55% reduction in losses and a 0.74% regression in voltage profile performance. After topology optimization, the loss profile improved by 65.08% and the voltage profile improved by 1.05%. Genetic algorithms are efficient and effective tools for improving the performance of distribution networks, whose degradation is often dynamic due to the natural variability of loads.展开更多
Deep learning(DL)is making significant inroads into biomedical imaging as it provides novel and powerful ways of accurately and efficiently improving the image quality of photoacoustic microscopy(PAM).Off-the-shelf DL...Deep learning(DL)is making significant inroads into biomedical imaging as it provides novel and powerful ways of accurately and efficiently improving the image quality of photoacoustic microscopy(PAM).Off-the-shelf DL models,however,do not necessarily obey the fundamental governing laws of PAM physical systems,nor do they generalize well to scenarios on which they have not been trained.In this work,a physics-embedded degeneration learning(PEDL)approach is proposed to enhance the image quality of PAM with a self-attention enhanced U-Net network,which obtains greater physical consistency,improves data efficiency,and higher adaptability.The proposed method is demonstrated on both synthetic and real datasets,including animal experiments in vivo(blood vessels of mouse's ear and brain).And the results show that compared with previous DL methods,the PEDL algorithm exhibits good performance in recovering PAM images qualitatively and quantitatively.It overcomes the challenges related to training data,accuracy,and robustness which a typical data-driven approach encounters,whose exemplary application envisions to provide a new perspective for existing DL tools of enhanced PAM.展开更多
Recent advancements in artificial intelligence have transformed three-dimensional(3D)optical imaging and metrology,enabling high-resolution and high-precision 3D surface geometry measurements from one single fringe pa...Recent advancements in artificial intelligence have transformed three-dimensional(3D)optical imaging and metrology,enabling high-resolution and high-precision 3D surface geometry measurements from one single fringe pattern projection.However,the imaging speed of conventional fringe projection profilometry(FPP)remains limited by the native sensor refresh rates due to the inherent"one-to-one"synchronization mechanism between pattern projection and image acquisition in standard structured light techniques.Here,we present dual-frequency angular-multiplexed fringe projection profilometry(DFAMFPP),a deep learning-enabled 3D imaging technique that achieves high-speed,high-precision,and large-depth-range absolute 3D surface measurements at speeds 16 times faster than the sensor's native frame rate.By encoding multi-timeframe 3D information into a single multiplexed image using multiple pairs of dual-frequency fringes,high-accuracy absolute phase maps are reconstructed using specially trained two-stage number-theoretical-based deep neural networks.We validate the effectiveness of DFAMFPP through dynamic scene measurements,achieving 10,000 Hz 3D imaging of a running turbofan engine prototype with only a 625 Hz camera.By overcoming the sensor hardware bottleneck,DFAMFPP significantly advances high-speed and ultra-high-speed 3D imaging,opening new avenues for exploring dynamic processes across diverse scientific disciplines.展开更多
The Chinese specification for trusted computing, which has similar functions with those defined by the Trusted Computing Group （TCG）, has adopted a different cryptography scheme. Applications designed for the TCG sp...The Chinese specification for trusted computing, which has similar functions with those defined by the Trusted Computing Group （TCG）, has adopted a different cryptography scheme. Applications designed for the TCG specifications cannot directly function on platforms complying with Chinese specifications because the two cryptography schemes are not compatible with each other. In order to transplant those applications with little to no modification, the paper presents a formal compatibility model based on Zaremski and Wing＇s type system. Our model is concerned not only on the syntactic compatibility for data type, but also on the semantic compatibility for cryptographic attributes according to the feature of trusted computing. A compatibility algorithm is proposed based on the model to generate adapters for trusted computing applications.展开更多
Soft computing(SC)refers to the ability of a digital computer or robot to perform functions that are normally associated with intelligent individuals,such as reasoning and problem-solving.An example of this would be a...Soft computing(SC)refers to the ability of a digital computer or robot to perform functions that are normally associated with intelligent individuals,such as reasoning and problem-solving.An example of this would be a project aimed at creating systems capable of reasoning,discovering meaning,generalising,or learning from past experience.Science and engineering problems that are both non-linear and complex can be solved using these methodologies.It has been proven that these algorithms can be used to solve numerous real-world problems.The techniques outlined can be used to increase the accuracy of existing models/equations,or they can be used to propose a newmodel that can address the problem.展开更多
Recent advancements in satellite technologies and the declining cost of access to space have led to the emergence of large satellite constellations in Low Earth Orbit(LEO).However,these constellations often rely on be...Recent advancements in satellite technologies and the declining cost of access to space have led to the emergence of large satellite constellations in Low Earth Orbit(LEO).However,these constellations often rely on bent-pipe architecture,resulting in high communication costs.Existing onboard inference architectures suffer from limitations in terms of low accuracy and inflexibility in the deployment and management of in-orbit applications.To address these challenges,we propose a cloud-native-based satellite design specifically tailored for Earth Observation tasks,enabling diverse computing paradigms.In this work,we present a case study of a satellite-ground collaborative inference system deployed in the Tiansuan constellation,demonstrating a remarkable 50%accuracy improvement and a substantial 90%data reduction.Our work sheds light on in-orbit energy,where in-orbit computing accounts for 17%of the total onboard energy consumption.Our approach represents a significant advancement of cloud-native satellite,aiming to enhance the accuracy of in-orbit computing while simultaneously reducing communication cost.展开更多
Computational Intelligent(CI)systems represent a pivotal intersection of cutting-edge technologies and complex engineering challenges aimed at solving real-world problems.This comprehensive body of work delves into th...Computational Intelligent(CI)systems represent a pivotal intersection of cutting-edge technologies and complex engineering challenges aimed at solving real-world problems.This comprehensive body of work delves into the realm of CI,which is designed to tackle intricate and multifaceted engineering problems through advanced computational techniques.The history of CI systems is a fascinating journey that spans several decades and has its roots in the development of artificial intelligence and machine learning techniques.Through a wide array of practical examples and case studies,this special issue bridges the gap between theoretical concepts and practical implementation,shedding light on how CI systems can optimize processes,design solutions,and inform decisions in complex engineering landscapes.This compilation stands as an essential resource for both novice learners and seasoned practitioners,offering a holistic perspective on the potential of CI in reshaping the future of engineering problem-solving.展开更多
This study attempts to accelerate the learning ability of an artificial electric field algorithm(AEFA)by attributing it with two mechanisms:elitism and opposition-based learning.Elitism advances the convergence of the...This study attempts to accelerate the learning ability of an artificial electric field algorithm(AEFA)by attributing it with two mechanisms:elitism and opposition-based learning.Elitism advances the convergence of the AEFA towards global optima by retaining the fine-tuned solutions obtained thus far,and opposition-based learning helps enhance its exploration ability.The new version of the AEFA,called elitist opposition leaning-based AEFA(EOAEFA),retains the properties of the basic AEFA while taking advantage of both elitism and opposition-based learning.Hence,the improved version attempts to reach optimum solutions by enabling the diversification of solutions with guaranteed convergence.Higher-order neural networks(HONNs)have single-layer adjustable parameters,fast learning,a robust fault tolerance,and good approximation ability compared with multilayer neural networks.They consider a higher order of input signals,increased the dimensionality of inputs through functional expansion and could thus discriminate between them.However,determining the number of expansion units in HONNs along with their associated parameters(i.e.,weight and threshold)is a bottleneck in the design of such networks.Here,we used EOAEFA to design two HONNs,namely,a pi-sigma neural network and a functional link artificial neural network,called EOAEFA-PSNN and EOAEFA-FLN,respectively,in a fully automated manner.The proposed models were evaluated on financial time-series datasets,focusing on predicting four closing prices,four exchange rates,and three energy prices.Experiments,comparative studies,and statistical tests were conducted to establish the efficacy of the proposed approach.展开更多
Covalent organic frameworks(COFs)have emerged as highly promising materials for high‐performance memristors due to their exceptional stability,molecular design flexibility,and tunable pore structures.However,the deve...Covalent organic frameworks(COFs)have emerged as highly promising materials for high‐performance memristors due to their exceptional stability,molecular design flexibility,and tunable pore structures.However,the development of COF memristors faces persistent challenges stemming from the structural disorder and quality control of COF films,which hinder the effective regulation of active metal ion migration during resistive switching.Herein,we report the synthesis of high‐quality,long‐range ordered,iminelinked two‐dimensional(2D)COFTP‐TD film via the innovative surface‐initiated polymerization(SIP)strategy.The long‐range ordered one‐dimensional(1D)nanochannels within 2D COFTP‐TD film facilitate the stable and directed growth of conductive filaments(CFs),further enhanced by imine–CFs coordination effects.As a result,the fabricated memristor devices exhibit exceptional multilevel nonvolatile memory performance,achieving an ON/OFF ratio of up to 106 and a retention time exceeding 2.0×105 s,marking a significant breakthrough in porous organic polymer(POP)memristors.Furthermore,the memristors demonstrate high‐precision waveform data recognition with an accuracy of 92.17%,comparable to software‐based recognition systems,highlighting its potential in advanced signal processing tasks.This study establishes a robust foundation for the development of high‐performance COF memristors and significantly broadens their application potential in neuromorphic computing.展开更多
Pn velocity lateral variation and anisotropy images were reconstructed by adding about 50 000 travel times from the regional seismic networks to the datum set of near 40 000 travel times from National Seismic Network ...Pn velocity lateral variation and anisotropy images were reconstructed by adding about 50 000 travel times from the regional seismic networks to the datum set of near 40 000 travel times from National Seismic Network of China used by WANG, et al. We discussed the relation of Pn velocity variation to Moho depth, Earths heat flow, distribution of Cenozoic volcanic rock and the result of rock experiment under high pressure and high temperature. The result of quantitative analysis indicates that Pn velocity is positively correlated with the crust thickness and negatively correlated with the Earths heat flow. Two linear regression equations, one between Pn velocity and crust thickness, and the other between Pn velocity and heat flow, were obtained. The rate of variation of Pn veloc-ity vP with pressure P, Pv/p, estimated from the velocity variation with crust thickness Hv/p, is close to the result obtained from the rock experiment under high pressure and high temperature. If the effect of crust thick-ness on Pn velocity is deducted from the velocity variation, then the low Pn velocity beneath Qinghai-Xizang pla-teau is more notable. The low Pn velocity regions well agree with the Cenozoic volcanic rock. In the several re-gions with significant anisotropy, the direction of fast Pn velocity is consistent with the orientation of maximum principal crustal compressive stress, and also with the direction of present-day crustal movement. It indicates that the fast Pn velocity direction may be related to the deformation or flow of top mantle material along the direction of maximum pressure.展开更多
Objective To compare the cognitive effects of guqin （the oldest Chinese instrument） music and piano music. Methods Behavioral and event-related potential （ERP） data in a standard two-stimulus auditory oddball task...Objective To compare the cognitive effects of guqin （the oldest Chinese instrument） music and piano music. Methods Behavioral and event-related potential （ERP） data in a standard two-stimulus auditory oddball task were recorded and analyzed. Results This study replicated the previous results of culture-familiar music effect on Chinese subjects： the greater P300 amplitude in frontal areas in a culture-familiar music environment. At the same time, the difference between guqin music and piano music was observed in NI and later positive complex （LPC： including P300 and P500）： a relatively higher participation of right anterior-temporal areas in Chinese subjects. Conclusion The results suggest that the special features of ERP responses to guqin music are the outcome of Chinese tonal language environments given the similarity between Guqin＇s tones and Mandarin lexical tones.展开更多
Based on fuzzy set theory, a fuzzy trust model is established by using membership function to describe the fuzziness of trust. The trust vectors of subjective trust are obtained based on a mathematical model of fuzzy ...Based on fuzzy set theory, a fuzzy trust model is established by using membership function to describe the fuzziness of trust. The trust vectors of subjective trust are obtained based on a mathematical model of fuzzy synthetic evaluation. Considering the complicated and changeable relationships between various subjects, the multi-level mathematical model of fuzzy synthetic evaluation is introduced. An example of a two-level fuzzy synthetic evaluation model confirms the feasibility of the multi-level fuzzy synthesis evaluation model. The proposed fuzzy model for trust evaluation may provide a promising method for research of trust model in open networks.展开更多
With the development of satellite technology,the satellite imagery of the earth’s surface and the whole surface makes it possible to survey surface resources and master the dynamic changes of the earth with high effi...With the development of satellite technology,the satellite imagery of the earth’s surface and the whole surface makes it possible to survey surface resources and master the dynamic changes of the earth with high efficiency and low consumption.As an important tool for satellite remote sensing image processing,remote sensing image classification has become a hot topic.According to the natural texture characteristics of remote sensing images,this paper combines different texture features with the Extreme Learning Machine,and proposes a new remote sensing image classification algorithm.The experimental tests are carried out through the standard test dataset SAT-4 and SAT-6.Our results show that the proposed method is a simpler and more efficient remote sensing image classification algorithm.It also achieves 99.434%recognition accuracy on SAT-4,which is 1.5%higher than the 97.95%accuracy achieved by DeepSat.At the same time,the recognition accuracy of SAT-6 reaches 99.5728%,which is 5.6%higher than DeepSat’s 93.9%.展开更多
Cluster tools have advantages of shorter cycle times,faster process development,and better yield for less contamination.The sequence of dual-arm cluster tools is a complex logistics process during the semiconductor pr...Cluster tools have advantages of shorter cycle times,faster process development,and better yield for less contamination.The sequence of dual-arm cluster tools is a complex logistics process during the semiconductor production.Efficient use of cluster tools is naturally very significant to competitive fab operations.Generating an optimized sequence in a computationally efficient manner and assessing the quality of the requirements to improve the fab production are the key factors for semiconductor manufacturing productivity.The Petri net modeling is introduced to minimize the makespan of the process for the three different logical modes and select a better mode after comparing the makespan among the three logical modes.The tool sequence optimization problem is formulated as optimization firing transition sequences based on the Petri net and then the formulation is converted to be linearly solved by the branch-and-cut method in the standard commercial solver CPLEX.Special methods for the linear conversion are highlighted.Due to the limited calculation time requirement for the real production and the large scale of the problem,special methods for the efficiency tuning are applied according to the characteristics of the problem.Numerical testing is supported by one of the most advanced semiconductor enterprises and the computational results show significant improvement compared with the traditional manual sequence results.展开更多
P-wave arrival times of both regional and teleseismic earthquakes were inverted to obtain mantle structures of East Asia. No fast （slab） velocity anomalies was not find beneath the 660-kin discontinuity through tomo...P-wave arrival times of both regional and teleseismic earthquakes were inverted to obtain mantle structures of East Asia. No fast （slab） velocity anomalies was not find beneath the 660-kin discontinuity through tomography besides a stagnant slab within the transition zone. Slow P-wave velocity anomalies are present at depths of 100-250 km below the active volcanic arc and East Asia. The western end of the flat stagnant slab is about 1 500 km west to active trench and may also be correlated with prominent surface topographic break in eastern China. We suggested that active mantle convection might be operating within this horizontally expanded ＂mantle wedge＂ above both the active subducting slabs and the stag- nant flat slabs beneath much of the North China plain. Both the widespread Cenozoic volcanism and associated extensional basins in East Asia could be the manifestation of this vigorous upper mantle convection. Cold or thermal alaomalies associated with the stagnant slabs above the 660-km discontinuity have not only caused a broad depression of the boundary due to its negative Clapeyron slope but also effectively shielded the asthenosphere and continental lithosphere above from any possible influence of mantle plumes in the lower mantle.展开更多
Unlike the shortest path problem that has only one optimal solution and can be solved in polynomial time, the muhi-objective shortest path problem （ MSPP ） has a set of pareto optimal solutions and cannot be solved ...Unlike the shortest path problem that has only one optimal solution and can be solved in polynomial time, the muhi-objective shortest path problem （ MSPP ） has a set of pareto optimal solutions and cannot be solved in polynomial time. The present algorithms focused mainly on how to obtain a precisely pareto optimal solution for MSPP resulting in a long time to obtain multiple pareto optimal solutions with them. In order to obtain a set of satisfied solutions for MSPP in reasonable time to meet the demand of a decision maker, a genetic algo- rithm MSPP-GA is presented to solve the MSPP with typically competing objectives, cost and time, in this pa- per. The encoding of the solution and the operators such as crossover, mutation and selection are developed. The algorithm introduced pareto domination tournament and sharing based selection operator, which can not only directly search the pareto optimal frontier but also maintain the diversity of populations in the process of evolutionary computation. Experimental results show that MSPP-GA can obtain most efficient solutions distributed all along the pareto frontier in less time than an exact algorithm. The algorithm proposed in this paper provides a new and effective method of how to obtain the set of pareto optimal solutions for other multiple objective optimization problems in a short time.展开更多
文摘Geo-engineering problems are known for their complexity and high uncertainty levels,requiring precise defini-tions,past experiences,logical reasoning,mathematical analysis,and practical insight to address them effectively.Soft Computing(SC)methods have gained popularity in engineering disciplines such as mining and civil engineering due to computer hardware and machine learning advancements.Unlike traditional hard computing approaches,SC models use soft values and fuzzy sets to navigate uncertain environments.This study focuses on the application of SC methods to predict backbreak,a common issue in blasting operations within mining and civil projects.Backbreak,which refers to the unintended fracturing of rock beyond the desired blast perimeter,can significantly impact project timelines and costs.This study aims to explore how SC methods can be effectively employed to anticipate and mitigate the undesirable consequences of blasting operations,specifically focusing on backbreak prediction.The research explores the complexities of backbreak prediction and highlights the potential benefits of utilizing SC methods to address this challenging issue in geo-engineering projects.
基金Anusandhan National Research Foundation(ANRF)(previously,Science and Engineering Research Board-SERB),India for the grant CRG/2022/002509.
文摘Rock slope along motorways in the Higher Himalayan terrains are prone to various types of failure.In order to effectively mitigate these failures,a thorough assessment of rock mass behavior is entailed.The present research employs and compares widely practiced geo-mechanical classification schemes viz.,RQD,RMR,SMR,Q-slope,and GSI.A 23 km road cut section,along Sangla to Chitkul route,in Higher Himalayan region(India)has been taken up for this work.Total of 18 locations were selected,and their slope and rockmass properties were examined.Afterwards,the most influencing parameters in RMR,SMR,and Q-Slope were evaluated through a machine learning algorithm,i.e.,Random Forest.For RMRbasic,about 83%of rock-slopes were designated in good condition and rest were of Fair quality.Evaluation of slope mass rating along all 18-locations highlighted eight-sites as partially unstable,six-sites as partially stable.Remaining four locations varied between,Very Bad to Bad slope-conditions,necessitating the installation of mechanical supports and redesign of slopes.For SMR classification,feature importance analysis revealed the predominance of F3 variable,RQD and intact rock strength.Q-Slope approach was incorporated to identify the most stable steepest angle of the examined locations.For Q-Slope rating,Jn and RQD were found to have the most influence in classification of the slopes.Three zones on the basis of GSI-scores have been identified in the study area,i.e.,A(6595),B(4555),and C(2535).This study highlights the application of multiple geomechanical classification schemes,demonstrating how each approach can complement the others.
文摘The distribution networks sometimes suffer from excessive losses and voltage violations in densely populated areas. The aim of the present study is to improve the performance of a distribution network by successively applying mono-capacitor positioning, multiple positioning and reconfiguration processes using GA-based algorithms implemented in a Matlab environment. From the diagnostic study of this network, it was observed that a minimum voltage of 0.90 pu induces a voltage deviation of 5.26%, followed by active and reactive losses of 425.08 kW and 435.09 kVAR, respectively. Single placement with the NSGAII resulted in the placement of a 3000 kVAR capacitor at node 128, which proved to be the invariably neuralgic point. Multiple placements resulted in a 21.55% reduction in losses and a 0.74% regression in voltage profile performance. After topology optimization, the loss profile improved by 65.08% and the voltage profile improved by 1.05%. Genetic algorithms are efficient and effective tools for improving the performance of distribution networks, whose degradation is often dynamic due to the natural variability of loads.
基金supported by National Natural Science Foundation of China(62227818,12204239,62275121)Youth Foundation of Jiangsu Province(BK20220946)+1 种基金Fundamental Research Funds for the Central Universities(30923011024)Open Research Fund of Jiangsu Key Laboratory of Spectral Imaging&Intelligent Sense(JSGP202201).
文摘Deep learning(DL)is making significant inroads into biomedical imaging as it provides novel and powerful ways of accurately and efficiently improving the image quality of photoacoustic microscopy(PAM).Off-the-shelf DL models,however,do not necessarily obey the fundamental governing laws of PAM physical systems,nor do they generalize well to scenarios on which they have not been trained.In this work,a physics-embedded degeneration learning(PEDL)approach is proposed to enhance the image quality of PAM with a self-attention enhanced U-Net network,which obtains greater physical consistency,improves data efficiency,and higher adaptability.The proposed method is demonstrated on both synthetic and real datasets,including animal experiments in vivo(blood vessels of mouse's ear and brain).And the results show that compared with previous DL methods,the PEDL algorithm exhibits good performance in recovering PAM images qualitatively and quantitatively.It overcomes the challenges related to training data,accuracy,and robustness which a typical data-driven approach encounters,whose exemplary application envisions to provide a new perspective for existing DL tools of enhanced PAM.
基金supported by National Key Research and Development Program of China(2022YFB2804603,2022YFB2804605)National Natural Science Foundation of China(U21B2033)+4 种基金Fundamental Research Funds forthe Central Universities(2023102001,2024202002)National Key Laborato-ry of Shock Wave and Detonation Physics(JCKYS2024212111)China Post-doctoral Science Fund(2023T160318)Open Research Fund of JiangsuKey Laboratory of Spectral Imaging&Intelligent Sense(JSGP202105,JSGP202201)Postgraduate Research&Practice Innovation Program of Jiangsu Province(KYCX25_0695,SJCX25_0188)。
文摘Recent advancements in artificial intelligence have transformed three-dimensional(3D)optical imaging and metrology,enabling high-resolution and high-precision 3D surface geometry measurements from one single fringe pattern projection.However,the imaging speed of conventional fringe projection profilometry(FPP)remains limited by the native sensor refresh rates due to the inherent"one-to-one"synchronization mechanism between pattern projection and image acquisition in standard structured light techniques.Here,we present dual-frequency angular-multiplexed fringe projection profilometry(DFAMFPP),a deep learning-enabled 3D imaging technique that achieves high-speed,high-precision,and large-depth-range absolute 3D surface measurements at speeds 16 times faster than the sensor's native frame rate.By encoding multi-timeframe 3D information into a single multiplexed image using multiple pairs of dual-frequency fringes,high-accuracy absolute phase maps are reconstructed using specially trained two-stage number-theoretical-based deep neural networks.We validate the effectiveness of DFAMFPP through dynamic scene measurements,achieving 10,000 Hz 3D imaging of a running turbofan engine prototype with only a 625 Hz camera.By overcoming the sensor hardware bottleneck,DFAMFPP significantly advances high-speed and ultra-high-speed 3D imaging,opening new avenues for exploring dynamic processes across diverse scientific disciplines.
基金Supported by the National High Technology Research and Development Plan of China (863 Program) (2006AA01Z440)the National Basic Research Program of China (973 Program) (2007CB311100)
文摘The Chinese specification for trusted computing, which has similar functions with those defined by the Trusted Computing Group （TCG）, has adopted a different cryptography scheme. Applications designed for the TCG specifications cannot directly function on platforms complying with Chinese specifications because the two cryptography schemes are not compatible with each other. In order to transplant those applications with little to no modification, the paper presents a formal compatibility model based on Zaremski and Wing＇s type system. Our model is concerned not only on the syntactic compatibility for data type, but also on the semantic compatibility for cryptographic attributes according to the feature of trusted computing. A compatibility algorithm is proposed based on the model to generate adapters for trusted computing applications.
文摘Soft computing(SC)refers to the ability of a digital computer or robot to perform functions that are normally associated with intelligent individuals,such as reasoning and problem-solving.An example of this would be a project aimed at creating systems capable of reasoning,discovering meaning,generalising,or learning from past experience.Science and engineering problems that are both non-linear and complex can be solved using these methodologies.It has been proven that these algorithms can be used to solve numerous real-world problems.The techniques outlined can be used to increase the accuracy of existing models/equations,or they can be used to propose a newmodel that can address the problem.
基金supported by National Natural Science Foundation of China(62032003).
文摘Recent advancements in satellite technologies and the declining cost of access to space have led to the emergence of large satellite constellations in Low Earth Orbit(LEO).However,these constellations often rely on bent-pipe architecture,resulting in high communication costs.Existing onboard inference architectures suffer from limitations in terms of low accuracy and inflexibility in the deployment and management of in-orbit applications.To address these challenges,we propose a cloud-native-based satellite design specifically tailored for Earth Observation tasks,enabling diverse computing paradigms.In this work,we present a case study of a satellite-ground collaborative inference system deployed in the Tiansuan constellation,demonstrating a remarkable 50%accuracy improvement and a substantial 90%data reduction.Our work sheds light on in-orbit energy,where in-orbit computing accounts for 17%of the total onboard energy consumption.Our approach represents a significant advancement of cloud-native satellite,aiming to enhance the accuracy of in-orbit computing while simultaneously reducing communication cost.
文摘Computational Intelligent(CI)systems represent a pivotal intersection of cutting-edge technologies and complex engineering challenges aimed at solving real-world problems.This comprehensive body of work delves into the realm of CI,which is designed to tackle intricate and multifaceted engineering problems through advanced computational techniques.The history of CI systems is a fascinating journey that spans several decades and has its roots in the development of artificial intelligence and machine learning techniques.Through a wide array of practical examples and case studies,this special issue bridges the gap between theoretical concepts and practical implementation,shedding light on how CI systems can optimize processes,design solutions,and inform decisions in complex engineering landscapes.This compilation stands as an essential resource for both novice learners and seasoned practitioners,offering a holistic perspective on the potential of CI in reshaping the future of engineering problem-solving.
基金supported by the Yonsei Fellow Program funded by Lee Youn Jae,Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korean government,Ministry of Science and ICT(MSIT)(No.2020-0-01361,Artificial Intelligence Graduate School Program(Yonsei University)No.2022-0-00113,Developing a Sustainable Collaborative Multi-modal Lifelong Learning Framework)the support of Teachers Associateship for Research Excellence(TARE)Fellowship(No.TAR/2021/00006)of the Science and Engineering Research Board(SERB),Government of India.
文摘This study attempts to accelerate the learning ability of an artificial electric field algorithm(AEFA)by attributing it with two mechanisms:elitism and opposition-based learning.Elitism advances the convergence of the AEFA towards global optima by retaining the fine-tuned solutions obtained thus far,and opposition-based learning helps enhance its exploration ability.The new version of the AEFA,called elitist opposition leaning-based AEFA(EOAEFA),retains the properties of the basic AEFA while taking advantage of both elitism and opposition-based learning.Hence,the improved version attempts to reach optimum solutions by enabling the diversification of solutions with guaranteed convergence.Higher-order neural networks(HONNs)have single-layer adjustable parameters,fast learning,a robust fault tolerance,and good approximation ability compared with multilayer neural networks.They consider a higher order of input signals,increased the dimensionality of inputs through functional expansion and could thus discriminate between them.However,determining the number of expansion units in HONNs along with their associated parameters(i.e.,weight and threshold)is a bottleneck in the design of such networks.Here,we used EOAEFA to design two HONNs,namely,a pi-sigma neural network and a functional link artificial neural network,called EOAEFA-PSNN and EOAEFA-FLN,respectively,in a fully automated manner.The proposed models were evaluated on financial time-series datasets,focusing on predicting four closing prices,four exchange rates,and three energy prices.Experiments,comparative studies,and statistical tests were conducted to establish the efficacy of the proposed approach.
基金supported by the National Key R&D Program of China(2021YFA1200501)the National Natural Science Foundation of China(U22A20137,U21A2069,22271110,and 62202350)the Shenzhen Science and Technology Innovation Program(JCYJ20220818102215033,GJHZ20240218114701003,JCYJ20230807143607016,GJHZ20210705142542015,and JCYJ20220530160811027).
文摘Covalent organic frameworks(COFs)have emerged as highly promising materials for high‐performance memristors due to their exceptional stability,molecular design flexibility,and tunable pore structures.However,the development of COF memristors faces persistent challenges stemming from the structural disorder and quality control of COF films,which hinder the effective regulation of active metal ion migration during resistive switching.Herein,we report the synthesis of high‐quality,long‐range ordered,iminelinked two‐dimensional(2D)COFTP‐TD film via the innovative surface‐initiated polymerization(SIP)strategy.The long‐range ordered one‐dimensional(1D)nanochannels within 2D COFTP‐TD film facilitate the stable and directed growth of conductive filaments(CFs),further enhanced by imine–CFs coordination effects.As a result,the fabricated memristor devices exhibit exceptional multilevel nonvolatile memory performance,achieving an ON/OFF ratio of up to 106 and a retention time exceeding 2.0×105 s,marking a significant breakthrough in porous organic polymer(POP)memristors.Furthermore,the memristors demonstrate high‐precision waveform data recognition with an accuracy of 92.17%,comparable to software‐based recognition systems,highlighting its potential in advanced signal processing tasks.This study establishes a robust foundation for the development of high‐performance COF memristors and significantly broadens their application potential in neuromorphic computing.
基金State Key Basic Research Project of Development and Programming Mechanism and Prediction of Continental Strong Earthquakes (G1998040700).
文摘Pn velocity lateral variation and anisotropy images were reconstructed by adding about 50 000 travel times from the regional seismic networks to the datum set of near 40 000 travel times from National Seismic Network of China used by WANG, et al. We discussed the relation of Pn velocity variation to Moho depth, Earths heat flow, distribution of Cenozoic volcanic rock and the result of rock experiment under high pressure and high temperature. The result of quantitative analysis indicates that Pn velocity is positively correlated with the crust thickness and negatively correlated with the Earths heat flow. Two linear regression equations, one between Pn velocity and crust thickness, and the other between Pn velocity and heat flow, were obtained. The rate of variation of Pn veloc-ity vP with pressure P, Pv/p, estimated from the velocity variation with crust thickness Hv/p, is close to the result obtained from the rock experiment under high pressure and high temperature. If the effect of crust thick-ness on Pn velocity is deducted from the velocity variation, then the low Pn velocity beneath Qinghai-Xizang pla-teau is more notable. The low Pn velocity regions well agree with the Cenozoic volcanic rock. In the several re-gions with significant anisotropy, the direction of fast Pn velocity is consistent with the orientation of maximum principal crustal compressive stress, and also with the direction of present-day crustal movement. It indicates that the fast Pn velocity direction may be related to the deformation or flow of top mantle material along the direction of maximum pressure.
文摘Objective To compare the cognitive effects of guqin （the oldest Chinese instrument） music and piano music. Methods Behavioral and event-related potential （ERP） data in a standard two-stimulus auditory oddball task were recorded and analyzed. Results This study replicated the previous results of culture-familiar music effect on Chinese subjects： the greater P300 amplitude in frontal areas in a culture-familiar music environment. At the same time, the difference between guqin music and piano music was observed in NI and later positive complex （LPC： including P300 and P500）： a relatively higher participation of right anterior-temporal areas in Chinese subjects. Conclusion The results suggest that the special features of ERP responses to guqin music are the outcome of Chinese tonal language environments given the similarity between Guqin＇s tones and Mandarin lexical tones.
文摘Based on fuzzy set theory, a fuzzy trust model is established by using membership function to describe the fuzziness of trust. The trust vectors of subjective trust are obtained based on a mathematical model of fuzzy synthetic evaluation. Considering the complicated and changeable relationships between various subjects, the multi-level mathematical model of fuzzy synthetic evaluation is introduced. An example of a two-level fuzzy synthetic evaluation model confirms the feasibility of the multi-level fuzzy synthesis evaluation model. The proposed fuzzy model for trust evaluation may provide a promising method for research of trust model in open networks.
基金This work was supported in part by national science foundation project of P.R.China under Grant No.61701554State Language Commission Key Project(ZDl135-39)+1 种基金First class courses(Digital Image Processing:KC2066)MUC 111 Project,Ministry of Education Collaborative Education Project(201901056009,201901160059,201901238038).
文摘With the development of satellite technology,the satellite imagery of the earth’s surface and the whole surface makes it possible to survey surface resources and master the dynamic changes of the earth with high efficiency and low consumption.As an important tool for satellite remote sensing image processing,remote sensing image classification has become a hot topic.According to the natural texture characteristics of remote sensing images,this paper combines different texture features with the Extreme Learning Machine,and proposes a new remote sensing image classification algorithm.The experimental tests are carried out through the standard test dataset SAT-4 and SAT-6.Our results show that the proposed method is a simpler and more efficient remote sensing image classification algorithm.It also achieves 99.434%recognition accuracy on SAT-4,which is 1.5%higher than the 97.95%accuracy achieved by DeepSat.At the same time,the recognition accuracy of SAT-6 reaches 99.5728%,which is 5.6%higher than DeepSat’s 93.9%.
基金the National Natural Science Foundation of China(No.60534010)the 111 Project (No.B08015)the Project of Ministry of Education (No.NCET-05-0294)
文摘Cluster tools have advantages of shorter cycle times,faster process development,and better yield for less contamination.The sequence of dual-arm cluster tools is a complex logistics process during the semiconductor production.Efficient use of cluster tools is naturally very significant to competitive fab operations.Generating an optimized sequence in a computationally efficient manner and assessing the quality of the requirements to improve the fab production are the key factors for semiconductor manufacturing productivity.The Petri net modeling is introduced to minimize the makespan of the process for the three different logical modes and select a better mode after comparing the makespan among the three logical modes.The tool sequence optimization problem is formulated as optimization firing transition sequences based on the Petri net and then the formulation is converted to be linearly solved by the branch-and-cut method in the standard commercial solver CPLEX.Special methods for the linear conversion are highlighted.Due to the limited calculation time requirement for the real production and the large scale of the problem,special methods for the efficiency tuning are applied according to the characteristics of the problem.Numerical testing is supported by one of the most advanced semiconductor enterprises and the computational results show significant improvement compared with the traditional manual sequence results.
基金grants(B-11440134,S-12002006)to Dapeng Zhao from the Japan Society for the Promotion of ScienceSupport for Shunping Pei came from a postdoct grant of Peking University+1 种基金supported by the National Natural Science Foundation of China(Nos.40125011,90814002 and 41074041)the Chinese Academy of Sciences(No.KZCX2-EW-QN102)
文摘P-wave arrival times of both regional and teleseismic earthquakes were inverted to obtain mantle structures of East Asia. No fast （slab） velocity anomalies was not find beneath the 660-kin discontinuity through tomography besides a stagnant slab within the transition zone. Slow P-wave velocity anomalies are present at depths of 100-250 km below the active volcanic arc and East Asia. The western end of the flat stagnant slab is about 1 500 km west to active trench and may also be correlated with prominent surface topographic break in eastern China. We suggested that active mantle convection might be operating within this horizontally expanded ＂mantle wedge＂ above both the active subducting slabs and the stag- nant flat slabs beneath much of the North China plain. Both the widespread Cenozoic volcanism and associated extensional basins in East Asia could be the manifestation of this vigorous upper mantle convection. Cold or thermal alaomalies associated with the stagnant slabs above the 660-km discontinuity have not only caused a broad depression of the boundary due to its negative Clapeyron slope but also effectively shielded the asthenosphere and continental lithosphere above from any possible influence of mantle plumes in the lower mantle.
文摘Unlike the shortest path problem that has only one optimal solution and can be solved in polynomial time, the muhi-objective shortest path problem （ MSPP ） has a set of pareto optimal solutions and cannot be solved in polynomial time. The present algorithms focused mainly on how to obtain a precisely pareto optimal solution for MSPP resulting in a long time to obtain multiple pareto optimal solutions with them. In order to obtain a set of satisfied solutions for MSPP in reasonable time to meet the demand of a decision maker, a genetic algo- rithm MSPP-GA is presented to solve the MSPP with typically competing objectives, cost and time, in this pa- per. The encoding of the solution and the operators such as crossover, mutation and selection are developed. The algorithm introduced pareto domination tournament and sharing based selection operator, which can not only directly search the pareto optimal frontier but also maintain the diversity of populations in the process of evolutionary computation. Experimental results show that MSPP-GA can obtain most efficient solutions distributed all along the pareto frontier in less time than an exact algorithm. The algorithm proposed in this paper provides a new and effective method of how to obtain the set of pareto optimal solutions for other multiple objective optimization problems in a short time.
