Ensuring the safety of Artificial Intelligence(AI)is essential for providing dependable services,especially in various sectors such as the military,education,healthcare,and automotive industries.A highly effective met...Ensuring the safety of Artificial Intelligence(AI)is essential for providing dependable services,especially in various sectors such as the military,education,healthcare,and automotive industries.A highly effective method to boost the precision and performance of an AI agent involves multi-configuration training,followed by thorough evaluation in a specific setting to gauge performance outcomes.This research thoroughly investigates the design of three AI agents,each configured with a different number of hidden units.The first agent is equipped with 128 hidden units,the second with 256,and the third with 512,all utilizing the Proximal Policy Optimizer(PPO)algorithm.Importantly,all agents are trained in a uniformenvironment using the Unity simulation platform,employing theMachine Learning Agents Toolkit(ML-agents)in conjunction with the PPOalgorithm enhanced by an Intrinsic Curiosity Module(PPO+ICM).Themain aim of this study is to clearly highlight the benefits and limitations of increasing the number of hidden units.The results convincingly show that expanding the hidden units to 512 leads to a notable 50% enhancement in the agent’s Goal(G)and a substantial 50% decrease in the Collision(C)value.This study offers a detailed analysis of how the number of hidden units affects AI agent performance using the Proximal Policy Optimizer(PPO)algorithm,augmentedwith an Intrinsic Curiosity Module(ICM).By systematically comparing agents with 128,256,and 512 hidden units in a controlled Unity environment,the research provides valuable insights into the connection between network complexity and task performance.Theconsistent use of the ML-Agents Toolkit ensures a standardized training process,facilitating direct comparisons between the different configurations.展开更多
This paper addresses the synchronization of follower agents’state vectors with that of a leader in high-order nonlinear multi-agent systems.The proposed low-complexity control scheme employs high-gain observers to es...This paper addresses the synchronization of follower agents’state vectors with that of a leader in high-order nonlinear multi-agent systems.The proposed low-complexity control scheme employs high-gain observers to estimate higher-order synchronization errors,enabling the controller to rely solely on relative output measurements.This approach significantly reduces the dependence on full-state information,which is often infeasible or costly in practical engineering applications.An output feedback control strategy is developed to overcome these limitations while ensuring robust and effective synchronization.Simulation results are provided to demonstrate the effectiveness of the proposed approach and validate the theoretical findings.展开更多
The advent of artificial intelligence(AI)has propelled augmented reality(AR)display technology to a pivotal juncture,positioning it as a contender for the next generation of mobile intelligent terminals.However,the pu...The advent of artificial intelligence(AI)has propelled augmented reality(AR)display technology to a pivotal juncture,positioning it as a contender for the next generation of mobile intelligent terminals.However,the pursuit of advanced AR displays,particularly those capable of delivering immersive 3D experiences,is significantly hindered by the performance limitations of current hardware and the complexity of system integration.In this study,we present an innovative multi-focal plane AR display system that integrates a non-orthogonal polarization-multiplexing metasurface,freeform optical elements,and an OLED display screen.All optical elements are integrated into a single solid-state architecture,based on a joint optimization design approach of ray tracing and diffraction theory.The multi-focal plane AR visual effect is realized by the compact and multiplexing metasurface,which performs distinct phase functions across diverse polarization channels.Meanwhile,freeform surfaces offer ample design flexibility for the collaborative optimization of multi-focal plane imaging and the see-through systems.Followed by a mechanical design and prototype assembly,we demonstrate the system's capabilities in real-time and multi-focal plane display.The digital images at all virtual image distances seamlessly integrate with the real environment,fully exhibiting the system's high parallelism and real-time interactivity.With the innovative design concept and joint design method,we believe that our work will spur more innovative and compact intelligent solutions for AR displays and inject new vitality into hybrid optical systems.展开更多
In the plethora of conceptual and algorithmic developments supporting data analytics and system modeling,humancentric pursuits assume a particular position owing to ways they emphasize and realize interaction between ...In the plethora of conceptual and algorithmic developments supporting data analytics and system modeling,humancentric pursuits assume a particular position owing to ways they emphasize and realize interaction between users and the data.We advocate that the level of abstraction,which can be flexibly adjusted,is conveniently realized through Granular Computing.Granular Computing is concerned with the development and processing information granules–formal entities which facilitate a way of organizing knowledge about the available data and relationships existing there.This study identifies the principles of Granular Computing,shows how information granules are constructed and subsequently used in describing relationships present among the data.展开更多
This paper addresses a target-enclosing problem for multiple spacecraft systems by proposing a two-layer affine formation control strategy. Compared with the existing methods,the adopted two-layer network structure in...This paper addresses a target-enclosing problem for multiple spacecraft systems by proposing a two-layer affine formation control strategy. Compared with the existing methods,the adopted two-layer network structure in this paper is generally directed, which is suitable for practical space missions. Firstly, distributed finite-time sliding-mode estimators and formation controllers in both layers are designed separately to improve the flexibility of the formation control system. By introducing the properties of affine transformation into formation control protocol design,the controllers can be used to track different time-varying target formation patterns. Besides, multilayer time-varying encirclements can be achieved with particular shapes to surround the moving target. In the sequel, by integrating adaptive neural networks and specialized artificial potential functions into backstepping controllers, the problems of uncertain Euler-Lagrange models, collision avoidance as well as formation reconfiguration are solved simultaneously. The stability of the proposed controllers is verified by the Lyapunov direct method. Finally, two simulation examples of triangle formation and more complex hexagon formation are presented to illustrate the feasibility of the theoretical results.展开更多
Stimulated Raman scattering(SRS)microscopy has the ability of noninvasive imaging of specific chemical bonds and been increasingly used in biomedicine in recent years.Two pulsed Gaussian beams are used in traditional ...Stimulated Raman scattering(SRS)microscopy has the ability of noninvasive imaging of specific chemical bonds and been increasingly used in biomedicine in recent years.Two pulsed Gaussian beams are used in traditional SRS microscopes,providing with high lateral and axial spatial resolution.Because of the tight focus of the Gaussian beam,such an SRS microscopy is difficult to be used for imaging deep targets in scattering tissues.The SRS microscopy based on Bessel beams can solve the imaging problem to a certain extent.Here,we establish a theoretical model to calculate the SRS signal excited by two Bessel beams by integrating the SRS signal generation theory with the fractal propagation method.The fractal model of refractive index turbulence is employed to generate the scattering tissues where the light transport is modeled by the beam propagation method.We model the scattering tissues containing chemicals,calculate the SRS signals stimulated by two Bessel beams,discuss the influence of the fractal model parameters on signal generation,and compare them with those generated by the Gaussian beams.The results show that,even though the modeling parameters have great influence on SRS signal generation,the Bessel beams-based SRS can generate signals in deeper scattering tissues.展开更多
The object detection technique depends on various methods for duplicating the dataset without adding more images.Data augmentation is a popularmethod that assists deep neural networks in achieving better generalizatio...The object detection technique depends on various methods for duplicating the dataset without adding more images.Data augmentation is a popularmethod that assists deep neural networks in achieving better generalization performance and can be seen as a type of implicit regularization.Thismethod is recommended in the casewhere the amount of high-quality data is limited,and gaining new examples is costly and time-consuming.In this paper,we trained YOLOv7 with a dataset that is part of the Open Images dataset that has 8,600 images with four classes(Car,Bus,Motorcycle,and Person).We used five different data augmentations techniques for duplicates and improvement of our dataset.The performance of the object detection algorithm was compared when using the proposed augmented dataset with a combination of two and three types of data augmentation with the result of the original data.The evaluation result for the augmented data gives a promising result for every object,and every kind of data augmentation gives a different improvement.The mAP@.5 of all classes was 76%,and F1-score was 74%.The proposed method increased the mAP@.5 value by+13%and F1-score by+10%for all objects.展开更多
Autonomous systems are an emerging AI technology functioning without human intervention underpinned by the latest advances in intelligence,cognition,computer,and systems sciences.This paper explores the intelligent an...Autonomous systems are an emerging AI technology functioning without human intervention underpinned by the latest advances in intelligence,cognition,computer,and systems sciences.This paper explores the intelligent and mathematical foundations of autonomous systems.It focuses on structural and behavioral properties that constitute the intelligent power of autonomous systems.It explains how system intelligence aggregates from reflexive,imperative,adaptive intelligence to autonomous and cognitive intelligence.A hierarchical intelligence model(HIM)is introduced to elaborate the evolution of human and system intelligence as an inductive process.The properties of system autonomy are formally analyzed towards a wide range of applications in computational intelligence and systems engineering.Emerging paradigms of autonomous systems including brain-inspired systems,cognitive robots,and autonomous knowledge learning systems are described.Advances in autonomous systems will pave a way towards highly intelligent machines for augmenting human capabilities.展开更多
The interpretability of deep learning models has emerged as a compelling area in artificial intelligence research.The safety criteria for medical imaging are highly stringent,and models are required for an explanation...The interpretability of deep learning models has emerged as a compelling area in artificial intelligence research.The safety criteria for medical imaging are highly stringent,and models are required for an explanation.However,existing convolutional neural network solutions for left ventricular segmentation are viewed in terms of inputs and outputs.Thus,the interpretability of CNNs has come into the spotlight.Since medical imaging data are limited,many methods to fine-tune medical imaging models that are popular in transfer models have been built using massive public Image Net datasets by the transfer learning method.Unfortunately,this generates many unreliable parameters and makes it difficult to generate plausible explanations from these models.In this study,we trained from scratch rather than relying on transfer learning,creating a novel interpretable approach for autonomously segmenting the left ventricle with a cardiac MRI.Our enhanced GPU training system implemented interpretable global average pooling for graphics using deep learning.The deep learning tasks were simplified.Simplification included data management,neural network architecture,and training.Our system monitored and analyzed the gradient changes of different layers with dynamic visualizations in real-time and selected the optimal deployment model.Our results demonstrated that the proposed method was feasible and efficient:the Dice coefficient reached 94.48%,and the accuracy reached 99.7%.It was found that no current transfer learning models could perform comparably to the ImageNet transfer learning architectures.This model is lightweight and more convenient to deploy on mobile devices than transfer learning models.展开更多
Since around 1980,a new generation of wireless technology has arisen approximately every 10 years.First-generation(1G)and secondgeneration(2G)began with voice and eventually introduced more and more data in third-gene...Since around 1980,a new generation of wireless technology has arisen approximately every 10 years.First-generation(1G)and secondgeneration(2G)began with voice and eventually introduced more and more data in third-generation(3G)and became highly popular in the fourthgeneration(4G).To increase the data rate along with low latency and mass connectivity the fifth-generation(5G)networks are being installed from 2020.However,the 5G technology will not be able to fulfill the data demand at the end of this decade.Therefore,it is expected that 6G communication networks will rise,providing better services through the implementation of new enabling technologies and allowing users to connect everywhere.6G technology would not be confined to cellular communications networks,but would also comply with non-terrestrial communication system requirements,such as satellite communication.The ultimate objectives of this work are to address the major challenges of the evolution of cellular communication networks and to discourse the recent growth of the industry based on the key scopes of application and challenges.The main areas of research topics are summarized into(i)major 6G wireless networkmilestones;(ii)key performance indicators;(iii)future new applications;and(iv)potential fields of research,challenges,and open issues.展开更多
Intrinsic motivation helps autonomous exploring agents traverse a larger portion of their environments.However,simulations of different learning environments in previous research show that after millions of timesteps ...Intrinsic motivation helps autonomous exploring agents traverse a larger portion of their environments.However,simulations of different learning environments in previous research show that after millions of timesteps of successful training,an intrinsically motivated agent may learn to act in ways unintended by the designer.This potential for unintended actions of autonomous exploring agents poses threats to the environment and humans if operated in the real world.We investigated this topic by using Unity’s MachineLearningAgent Toolkit(ML-Agents)implementation of the Proximal Policy Optimization(PPO)algorithm with the Intrinsic Curiosity Module(ICM)to train autonomous exploring agents in three learning environments.We demonstrate that ICM,although designed to assist agent navigation in environments with sparse reward generation,increasing gradually as a tool for purposely training misbehaving agent in significantly less than 1 million timesteps.We present the following achievements:1)experiments designed to cause agents to act undesirably,2)a metric for gauging how well an agent achieves its goal without collisions,and 3)validation of PPO best practices.Then,we used optimized methods to improve the agent’s performance and reduce collisions within the same environments.These achievements help further our understanding of the significance of monitoring training statistics during reinforcement learning for determining how humans can intervene to improve agent safety and performance.展开更多
In this paper, the output feedback based finitehorizon near optimal regulation of nonlinear affine discretetime systems with unknown system dynamics is considered by using neural networks(NNs) to approximate Hamilton-...In this paper, the output feedback based finitehorizon near optimal regulation of nonlinear affine discretetime systems with unknown system dynamics is considered by using neural networks(NNs) to approximate Hamilton-JacobiBellman(HJB) equation solution. First, a NN-based Luenberger observer is proposed to reconstruct both the system states and the control coefficient matrix. Next, reinforcement learning methodology with actor-critic structure is utilized to approximate the time-varying solution, referred to as the value function, of the HJB equation by using a NN. To properly satisfy the terminal constraint, a new error term is defined and incorporated in the NN update law so that the terminal constraint error is also minimized over time. The NN with constant weights and timedependent activation function is employed to approximate the time-varying value function which is subsequently utilized to generate the finite-horizon near optimal control policy due to NN reconstruction errors. The proposed scheme functions in a forward-in-time manner without offline training phase. Lyapunov analysis is used to investigate the stability of the overall closedloop system. Simulation results are given to show the effectiveness and feasibility of the proposed method.展开更多
The method of stabilizing switched systems based on the optimal control is applied,with all modes unstable,for a typical example of the multi-agent system.First,the optimal control method for stabilizing switched syst...The method of stabilizing switched systems based on the optimal control is applied,with all modes unstable,for a typical example of the multi-agent system.First,the optimal control method for stabilizing switched systems is introduced.For this purpose,a switching table rule procedure is constructed.This procedure is inspired by the optimal control that identifies the optimal trajectory for the switched systems.In the next step,the stability of a multi-agent system is studied,considering different unstable connection topologies.Finally,the optimal control method is successfully applied to an aircraft team,as an example of the multi-agent systems.Simulation results evaluate and confirm the successful application of this method in the aircraft team example.展开更多
Even for a 100 nm interparticle distance or a small change in particle shape,optical Fano-like plasmonic resonance mode usually vanishes completely.It would be remarkable if stable Fano-like resonance could somehow be...Even for a 100 nm interparticle distance or a small change in particle shape,optical Fano-like plasmonic resonance mode usually vanishes completely.It would be remarkable if stable Fano-like resonance could somehow be achieved in distinctly shaped nanoparticles for more than 1μm interparticle distance,which corresponds to the far electromagnetic field region.If such far-field Fano-like plasmonic resonance can be achieved,controlling the reversal of the far-field binding force can be attained,like the currently reported reversals for near-field cases.In this work,we have proposed an optical set-up to achieve such a robust and stable Fano-like plasmonic resonance,and comparatively studied its remarkable impact on controlling the reversal of near-and far-field optical binding forces.In our proposed set-up,the distinctly shaped plasmonic tetramers are half immersed(i.e.air-benzene)in an inhomogeneous dielectric interface and illuminated by?circular?polarized light.We have demonstrated significant differences between near-and far-field optical binding forces along with the Lorentz force field,which partially depends on the object’s shape.A clear connection is shown between the far-field binding force and the resonant modes,along with a generic mechanism to achieve controllable Fano-like plasmonic resonance and the reversal of the optical binding force in both far-and near-field configurations.展开更多
Two-dimensional(2D) alternating cation(ACI) perovskite surface defects,especially dominant iodine vacancies(V_Ⅰ) and undercoordinated Pb^(2+),limit the performance of perovskite solar cells(PVSCs).To address the issu...Two-dimensional(2D) alternating cation(ACI) perovskite surface defects,especially dominant iodine vacancies(V_Ⅰ) and undercoordinated Pb^(2+),limit the performance of perovskite solar cells(PVSCs).To address the issue,1-butyl-3-methylimidazolium trifluoro-methane-sulfonate(BMIMOTF) and its iodide counterpart(BMIMI) are utilized to modify the perovskite surface respectively.We find that BMIMI can change the perovskite surface,whereas BMIMOTF shows a nondestructive and more effective defect passivation,giving significantly reduced defect density and suppressed charge-carrier nonradiative recombination.This mainly attributes to the marked passivation efficacy of OTF-anion on V_Ⅰ and undercoordinated Pb^(2+),rather than BMIMI^(+) cation.Benefiting from the rational surface-modification of BMMIMOTF,the films exhibit an optimized energy level alignment,enhanced hydrophobicity and suppressed ion migration.Consequently,the BMIMOTF-modified devices achieve an impressive efficiency of 21.38% with a record open-circuit voltage of 1.195 V,which is among the best efficiencies reported for 2D PVSCs,and display greatly enhanced humidity and thermal stability.展开更多
Considering the inhomogeneous or heterogeneous background, we have demonstrated that if the background and the half-immersed object are both non-absorbing, the transferred photon momentum to the pulled object can be c...Considering the inhomogeneous or heterogeneous background, we have demonstrated that if the background and the half-immersed object are both non-absorbing, the transferred photon momentum to the pulled object can be considered as the one of Minkowski exactly at the interface. In contrast, the presence of loss inside matter, either in the half-immersed object or in the background, causes optical pushing of the object. Our analysis suggests that for half-immersed plasmonic or lossy dielectric, the transferred momentum of photon can mathematically be modeled as the type of Minkowski and also of Abraham. However, according to a final critical analysis, the idea of Abraham momentum transfer has been rejected. Hence,an obvious question arises: whence the Abraham momentum? It is demonstrated that though the transferred momentum to a half-immersed Mie object(lossy or lossless) can better be considered as the Minkowski momentum, Lorentz force analysis suggests that the momentum of a photon traveling through the continuous background, however, can be modeled as the type of Abraham. Finally, as an interesting sidewalk, a machine learning based system has been developed to predict the time-averaged force within a very short time avoiding time-consuming full wave simulation.展开更多
A photovoltaic technology historically goes through two major steps to evolve into a mature technology. The first step involves advances in materials and is usually accompanied by the rapid improvement of power conver...A photovoltaic technology historically goes through two major steps to evolve into a mature technology. The first step involves advances in materials and is usually accompanied by the rapid improvement of power conversion efficiency. The second step focuses on interfaces and is usually accompanied by significant stability improvement. As an emerging generation of photovoltaic technology, perovskite solar cells are transitioning to the second step of their development when a significant focus shifts toward interface studies and engineering. While various interface engineering strategies have been developed, interfacial characterization is crucial to show the effectiveness of interfacial modification. Here, we review the characterization techniques that have been utilized in studying interface properties in perovskite solar cells. We first summarize the main roles of interfaces in perovskite solar cells, and then we discuss some typical characterization methodologies for morphological, optical,and electrical studies of interfaces. Successful experiences and existing problems are analyzed when discussing some commonly used methods. We then analyze the challenges and provide an outlook for further development of interfacial characterizations. This review aims to evoke strengthened research devotion on novel and persuasive interfacial engineering.展开更多
In order to accommodate the large number of Internet of Things(IoT)connections in mobile networks,Non-Orthogonal Multiple Access(NOMA)has been applied as the resource sharing mechanism in mobile access networks to imp...In order to accommodate the large number of Internet of Things(IoT)connections in mobile networks,Non-Orthogonal Multiple Access(NOMA)has been applied as the resource sharing mechanism in mobile access networks to improve the spectrum efficiency.The NOMA-based resource management for uplink communications comprises two problems,i.e.,user clustering and power&wireless channel allocation.User clustering refers to assigning users in terms of IoT devices to different clusters(where users in the same cluster are sharing the wireless channels to upload their data),and power&wireless channel allocation is to optimize the transmission power of the users and the number of wireless channels allocated to the users in a cluster.The two problems are coupled together,thus making it difficult to solve the NOMA-based resource management problem.In this paper,we propose a QoS-aWarE resourcE managemenT(SWEET)for NOMA algorithm to jointly optimize the user clustering,power management,and wireless channel allocation such that the number of wireless channels is minimized and the data rate requirements of the users can be satisfied.The performance of SWEET is validated via extensive simulations.展开更多
Multi-Agent Reinforcement Learning(MARL)has proven to be successful in cooperative assignments.MARL is used to investigate how autonomous agents with the same interests can connect and act in one team.MARL cooperation...Multi-Agent Reinforcement Learning(MARL)has proven to be successful in cooperative assignments.MARL is used to investigate how autonomous agents with the same interests can connect and act in one team.MARL cooperation scenarios are explored in recreational cooperative augmented reality environments,as well as realworld scenarios in robotics.In this paper,we explore the realm of MARL and its potential applications in cooperative assignments.Our focus is on developing a multi-agent system that can collaborate to attack or defend against enemies and achieve victory withminimal damage.To accomplish this,we utilize the StarCraftMulti-Agent Challenge(SMAC)environment and train four MARL algorithms:Q-learning with Mixtures of Experts(QMIX),Value-DecompositionNetwork(VDN),Multi-agent Proximal PolicyOptimizer(MAPPO),andMulti-Agent Actor Attention Critic(MAA2C).These algorithms allow multiple agents to cooperate in a specific scenario to achieve the targeted mission.Our results show that the QMIX algorithm outperforms the other three algorithms in the attacking scenario,while the VDN algorithm achieves the best results in the defending scenario.Specifically,the VDNalgorithmreaches the highest value of battle wonmean and the lowest value of dead alliesmean.Our research demonstrates the potential forMARL algorithms to be used in real-world applications,such as controllingmultiple robots to provide helpful services or coordinating teams of agents to accomplish tasks that would be impossible for a human to do.The SMAC environment provides a unique opportunity to test and evaluate MARL algorithms in a challenging and dynamic environment,and our results show that these algorithms can be used to achieve victory with minimal damage.展开更多
Piezoelectric ultrasonic transducers have shown great potential in biomedical applications due to their high acoustic-to-electric conversion efficiency and large power capacity.The focusing technique enables the trans...Piezoelectric ultrasonic transducers have shown great potential in biomedical applications due to their high acoustic-to-electric conversion efficiency and large power capacity.The focusing technique enables the transducer to produce an extremely narrow beam,greatly improving the resolution and sensitivity.In this work,we summarize the fundamental properties and biological effects of the ultrasound field,aiming to establish a correlation between device design and application.Focusing techniques for piezoelectric transducers are highlighted,including material selection and fabrication methods,which determine the final performance of piezoelectric transducers.Numerous examples,from ultrasound imaging,neuromodulation,tumor ablation to ultrasonic wireless energy transfer,are summarized to highlight the great promise of biomedical applications.Finally,the challenges and opportunities of focused ultrasound transducers are presented.The aim of this review is to bridge the gap between focused ultrasound systems and biomedical applications.展开更多
基金supported by the United States Air Force Office of Scientific Research(AFOSR)contract FA9550-22-1-0268 awarded to KHA,https://www.afrl.af.mil/AFOSR/.
文摘Ensuring the safety of Artificial Intelligence(AI)is essential for providing dependable services,especially in various sectors such as the military,education,healthcare,and automotive industries.A highly effective method to boost the precision and performance of an AI agent involves multi-configuration training,followed by thorough evaluation in a specific setting to gauge performance outcomes.This research thoroughly investigates the design of three AI agents,each configured with a different number of hidden units.The first agent is equipped with 128 hidden units,the second with 256,and the third with 512,all utilizing the Proximal Policy Optimizer(PPO)algorithm.Importantly,all agents are trained in a uniformenvironment using the Unity simulation platform,employing theMachine Learning Agents Toolkit(ML-agents)in conjunction with the PPOalgorithm enhanced by an Intrinsic Curiosity Module(PPO+ICM).Themain aim of this study is to clearly highlight the benefits and limitations of increasing the number of hidden units.The results convincingly show that expanding the hidden units to 512 leads to a notable 50% enhancement in the agent’s Goal(G)and a substantial 50% decrease in the Collision(C)value.This study offers a detailed analysis of how the number of hidden units affects AI agent performance using the Proximal Policy Optimizer(PPO)algorithm,augmentedwith an Intrinsic Curiosity Module(ICM).By systematically comparing agents with 128,256,and 512 hidden units in a controlled Unity environment,the research provides valuable insights into the connection between network complexity and task performance.Theconsistent use of the ML-Agents Toolkit ensures a standardized training process,facilitating direct comparisons between the different configurations.
文摘This paper addresses the synchronization of follower agents’state vectors with that of a leader in high-order nonlinear multi-agent systems.The proposed low-complexity control scheme employs high-gain observers to estimate higher-order synchronization errors,enabling the controller to rely solely on relative output measurements.This approach significantly reduces the dependence on full-state information,which is often infeasible or costly in practical engineering applications.An output feedback control strategy is developed to overcome these limitations while ensuring robust and effective synchronization.Simulation results are provided to demonstrate the effectiveness of the proposed approach and validate the theoretical findings.
基金funding provided by National Natural Science Foundation of China(U21A20140)National Key Research and Development Program of China(2021YFA1401200)+2 种基金Beijing Natural Science Foundation(JQ24028)Beijing Nova Program(20240484557)Synergetic Extreme Condition User Facility(SECUF).
文摘The advent of artificial intelligence(AI)has propelled augmented reality(AR)display technology to a pivotal juncture,positioning it as a contender for the next generation of mobile intelligent terminals.However,the pursuit of advanced AR displays,particularly those capable of delivering immersive 3D experiences,is significantly hindered by the performance limitations of current hardware and the complexity of system integration.In this study,we present an innovative multi-focal plane AR display system that integrates a non-orthogonal polarization-multiplexing metasurface,freeform optical elements,and an OLED display screen.All optical elements are integrated into a single solid-state architecture,based on a joint optimization design approach of ray tracing and diffraction theory.The multi-focal plane AR visual effect is realized by the compact and multiplexing metasurface,which performs distinct phase functions across diverse polarization channels.Meanwhile,freeform surfaces offer ample design flexibility for the collaborative optimization of multi-focal plane imaging and the see-through systems.Followed by a mechanical design and prototype assembly,we demonstrate the system's capabilities in real-time and multi-focal plane display.The digital images at all virtual image distances seamlessly integrate with the real environment,fully exhibiting the system's high parallelism and real-time interactivity.With the innovative design concept and joint design method,we believe that our work will spur more innovative and compact intelligent solutions for AR displays and inject new vitality into hybrid optical systems.
文摘In the plethora of conceptual and algorithmic developments supporting data analytics and system modeling,humancentric pursuits assume a particular position owing to ways they emphasize and realize interaction between users and the data.We advocate that the level of abstraction,which can be flexibly adjusted,is conveniently realized through Granular Computing.Granular Computing is concerned with the development and processing information granules–formal entities which facilitate a way of organizing knowledge about the available data and relationships existing there.This study identifies the principles of Granular Computing,shows how information granules are constructed and subsequently used in describing relationships present among the data.
基金sponsored by National Natural Science Foundation of China (Nos. 61673327, 51606161, 11602209, 91441128)Natural Science Foundation of Fujian Province of China (No. 2016J06011)China Scholarship Council (No. 201606310153)
文摘This paper addresses a target-enclosing problem for multiple spacecraft systems by proposing a two-layer affine formation control strategy. Compared with the existing methods,the adopted two-layer network structure in this paper is generally directed, which is suitable for practical space missions. Firstly, distributed finite-time sliding-mode estimators and formation controllers in both layers are designed separately to improve the flexibility of the formation control system. By introducing the properties of affine transformation into formation control protocol design,the controllers can be used to track different time-varying target formation patterns. Besides, multilayer time-varying encirclements can be achieved with particular shapes to surround the moving target. In the sequel, by integrating adaptive neural networks and specialized artificial potential functions into backstepping controllers, the problems of uncertain Euler-Lagrange models, collision avoidance as well as formation reconfiguration are solved simultaneously. The stability of the proposed controllers is verified by the Lyapunov direct method. Finally, two simulation examples of triangle formation and more complex hexagon formation are presented to illustrate the feasibility of the theoretical results.
基金This work was supported in part by the National Key R&D Program of China under Grant No.2018YFC0910600the National Natural Science Foundation of China under Grant Nos.81871397,81627807,11727813,91859109+2 种基金the Shaanxi Science Fund for Distinguished Young Scholars under Grant No.2020JC-27the Shaanxi Young Top-notch Talent of"Special Support Program"the Best Funded Projects for the Scientific and Technological Activities for Excellent Overseas Researchers in Shaanxi Province(2017017)..
文摘Stimulated Raman scattering(SRS)microscopy has the ability of noninvasive imaging of specific chemical bonds and been increasingly used in biomedicine in recent years.Two pulsed Gaussian beams are used in traditional SRS microscopes,providing with high lateral and axial spatial resolution.Because of the tight focus of the Gaussian beam,such an SRS microscopy is difficult to be used for imaging deep targets in scattering tissues.The SRS microscopy based on Bessel beams can solve the imaging problem to a certain extent.Here,we establish a theoretical model to calculate the SRS signal excited by two Bessel beams by integrating the SRS signal generation theory with the fractal propagation method.The fractal model of refractive index turbulence is employed to generate the scattering tissues where the light transport is modeled by the beam propagation method.We model the scattering tissues containing chemicals,calculate the SRS signals stimulated by two Bessel beams,discuss the influence of the fractal model parameters on signal generation,and compare them with those generated by the Gaussian beams.The results show that,even though the modeling parameters have great influence on SRS signal generation,the Bessel beams-based SRS can generate signals in deeper scattering tissues.
基金the United States Air Force Office of Scientific Research(AFOSR)contract FA9550-22-1-0268 awarded to KHA,https://www.afrl.af.mil/AFOSR/.The contract is entitled:“Investigating Improving Safety of Autonomous Exploring Intelligent Agents with Human-in-the-Loop Reinforcement Learning,”and in part by Jackson State University.
文摘The object detection technique depends on various methods for duplicating the dataset without adding more images.Data augmentation is a popularmethod that assists deep neural networks in achieving better generalization performance and can be seen as a type of implicit regularization.Thismethod is recommended in the casewhere the amount of high-quality data is limited,and gaining new examples is costly and time-consuming.In this paper,we trained YOLOv7 with a dataset that is part of the Open Images dataset that has 8,600 images with four classes(Car,Bus,Motorcycle,and Person).We used five different data augmentations techniques for duplicates and improvement of our dataset.The performance of the object detection algorithm was compared when using the proposed augmented dataset with a combination of two and three types of data augmentation with the result of the original data.The evaluation result for the augmented data gives a promising result for every object,and every kind of data augmentation gives a different improvement.The mAP@.5 of all classes was 76%,and F1-score was 74%.The proposed method increased the mAP@.5 value by+13%and F1-score by+10%for all objects.
基金supported in part by the Department of National Defence’s Innovation for Defence Excellence and Security(IDEa S)Program,Canadathrough the Project of Auto Defence Towards Trustworthy Technologies for Autonomous Human-Machine Systems,NSERCthe IEEE SMC Society Technical Committee on Brain-Inspired Systems(TCBCS)。
文摘Autonomous systems are an emerging AI technology functioning without human intervention underpinned by the latest advances in intelligence,cognition,computer,and systems sciences.This paper explores the intelligent and mathematical foundations of autonomous systems.It focuses on structural and behavioral properties that constitute the intelligent power of autonomous systems.It explains how system intelligence aggregates from reflexive,imperative,adaptive intelligence to autonomous and cognitive intelligence.A hierarchical intelligence model(HIM)is introduced to elaborate the evolution of human and system intelligence as an inductive process.The properties of system autonomy are formally analyzed towards a wide range of applications in computational intelligence and systems engineering.Emerging paradigms of autonomous systems including brain-inspired systems,cognitive robots,and autonomous knowledge learning systems are described.Advances in autonomous systems will pave a way towards highly intelligent machines for augmenting human capabilities.
基金The National Natural Science Foundation of China (62176048)provided funding for this research.
文摘The interpretability of deep learning models has emerged as a compelling area in artificial intelligence research.The safety criteria for medical imaging are highly stringent,and models are required for an explanation.However,existing convolutional neural network solutions for left ventricular segmentation are viewed in terms of inputs and outputs.Thus,the interpretability of CNNs has come into the spotlight.Since medical imaging data are limited,many methods to fine-tune medical imaging models that are popular in transfer models have been built using massive public Image Net datasets by the transfer learning method.Unfortunately,this generates many unreliable parameters and makes it difficult to generate plausible explanations from these models.In this study,we trained from scratch rather than relying on transfer learning,creating a novel interpretable approach for autonomously segmenting the left ventricle with a cardiac MRI.Our enhanced GPU training system implemented interpretable global average pooling for graphics using deep learning.The deep learning tasks were simplified.Simplification included data management,neural network architecture,and training.Our system monitored and analyzed the gradient changes of different layers with dynamic visualizations in real-time and selected the optimal deployment model.Our results demonstrated that the proposed method was feasible and efficient:the Dice coefficient reached 94.48%,and the accuracy reached 99.7%.It was found that no current transfer learning models could perform comparably to the ImageNet transfer learning architectures.This model is lightweight and more convenient to deploy on mobile devices than transfer learning models.
基金This research was supported by the National Research Foundation(NRF),Korea(2019R1C1C1007277)funded by the Ministry of Science and ICT(MSIT),Korea.
文摘Since around 1980,a new generation of wireless technology has arisen approximately every 10 years.First-generation(1G)and secondgeneration(2G)began with voice and eventually introduced more and more data in third-generation(3G)and became highly popular in the fourthgeneration(4G).To increase the data rate along with low latency and mass connectivity the fifth-generation(5G)networks are being installed from 2020.However,the 5G technology will not be able to fulfill the data demand at the end of this decade.Therefore,it is expected that 6G communication networks will rise,providing better services through the implementation of new enabling technologies and allowing users to connect everywhere.6G technology would not be confined to cellular communications networks,but would also comply with non-terrestrial communication system requirements,such as satellite communication.The ultimate objectives of this work are to address the major challenges of the evolution of cellular communication networks and to discourse the recent growth of the industry based on the key scopes of application and challenges.The main areas of research topics are summarized into(i)major 6G wireless networkmilestones;(ii)key performance indicators;(iii)future new applications;and(iv)potential fields of research,challenges,and open issues.
基金This work was partly supported by the United States Air Force Office of Scientific Research(AFOSR)contract FA9550-22-1-0268 awarded to KHA,https://www.afrl.af.mil/AFOSR/.The contract is entitled:“Investigating Improving Safety of Autonomous Exploring Intelligent Agents with Human-in-the-Loop Reinforcement Learning,”and in part by Jackson State University。
文摘Intrinsic motivation helps autonomous exploring agents traverse a larger portion of their environments.However,simulations of different learning environments in previous research show that after millions of timesteps of successful training,an intrinsically motivated agent may learn to act in ways unintended by the designer.This potential for unintended actions of autonomous exploring agents poses threats to the environment and humans if operated in the real world.We investigated this topic by using Unity’s MachineLearningAgent Toolkit(ML-Agents)implementation of the Proximal Policy Optimization(PPO)algorithm with the Intrinsic Curiosity Module(ICM)to train autonomous exploring agents in three learning environments.We demonstrate that ICM,although designed to assist agent navigation in environments with sparse reward generation,increasing gradually as a tool for purposely training misbehaving agent in significantly less than 1 million timesteps.We present the following achievements:1)experiments designed to cause agents to act undesirably,2)a metric for gauging how well an agent achieves its goal without collisions,and 3)validation of PPO best practices.Then,we used optimized methods to improve the agent’s performance and reduce collisions within the same environments.These achievements help further our understanding of the significance of monitoring training statistics during reinforcement learning for determining how humans can intervene to improve agent safety and performance.
文摘In this paper, the output feedback based finitehorizon near optimal regulation of nonlinear affine discretetime systems with unknown system dynamics is considered by using neural networks(NNs) to approximate Hamilton-JacobiBellman(HJB) equation solution. First, a NN-based Luenberger observer is proposed to reconstruct both the system states and the control coefficient matrix. Next, reinforcement learning methodology with actor-critic structure is utilized to approximate the time-varying solution, referred to as the value function, of the HJB equation by using a NN. To properly satisfy the terminal constraint, a new error term is defined and incorporated in the NN update law so that the terminal constraint error is also minimized over time. The NN with constant weights and timedependent activation function is employed to approximate the time-varying value function which is subsequently utilized to generate the finite-horizon near optimal control policy due to NN reconstruction errors. The proposed scheme functions in a forward-in-time manner without offline training phase. Lyapunov analysis is used to investigate the stability of the overall closedloop system. Simulation results are given to show the effectiveness and feasibility of the proposed method.
文摘The method of stabilizing switched systems based on the optimal control is applied,with all modes unstable,for a typical example of the multi-agent system.First,the optimal control method for stabilizing switched systems is introduced.For this purpose,a switching table rule procedure is constructed.This procedure is inspired by the optimal control that identifies the optimal trajectory for the switched systems.In the next step,the stability of a multi-agent system is studied,considering different unstable connection topologies.Finally,the optimal control method is successfully applied to an aircraft team,as an example of the multi-agent systems.Simulation results evaluate and confirm the successful application of this method in the aircraft team example.
基金the support of the internal grant of North South University 2018–19 and 2019–20(approved by the members of BOT,North South University,Bangladesh)along with the support of a TWAS international grant 2018–19(18-121 RG/PHYS/AS_I).
文摘Even for a 100 nm interparticle distance or a small change in particle shape,optical Fano-like plasmonic resonance mode usually vanishes completely.It would be remarkable if stable Fano-like resonance could somehow be achieved in distinctly shaped nanoparticles for more than 1μm interparticle distance,which corresponds to the far electromagnetic field region.If such far-field Fano-like plasmonic resonance can be achieved,controlling the reversal of the far-field binding force can be attained,like the currently reported reversals for near-field cases.In this work,we have proposed an optical set-up to achieve such a robust and stable Fano-like plasmonic resonance,and comparatively studied its remarkable impact on controlling the reversal of near-and far-field optical binding forces.In our proposed set-up,the distinctly shaped plasmonic tetramers are half immersed(i.e.air-benzene)in an inhomogeneous dielectric interface and illuminated by?circular?polarized light.We have demonstrated significant differences between near-and far-field optical binding forces along with the Lorentz force field,which partially depends on the object’s shape.A clear connection is shown between the far-field binding force and the resonant modes,along with a generic mechanism to achieve controllable Fano-like plasmonic resonance and the reversal of the optical binding force in both far-and near-field configurations.
基金financially supported by the National Natural Science Foundation of China (62174021 and 62104028)the Creative Research Groups of the National Natural Science Foundation of Sichuan Province (2023NSFSC1973)+7 种基金the Sichuan Science and Technology Program (MZGC20230008)the Natural Science Foundation of Sichuan Province (2022NSFSC0899)the China Postdoctoral Science Foundation (2021M700689)the Grant SCITLAB (20012) of Intelligent Terminal Key Laboratory of Sichuan ProvinceFundamental Research Funds for the Central Universities (ZYGX2019J054)the Guangdong Basic and Applied Basic Research Foundation (2019A1515110438)sponsored by the University of Kentuckythe Sichuan Province Key Laboratory of Display Science and Technology。
文摘Two-dimensional(2D) alternating cation(ACI) perovskite surface defects,especially dominant iodine vacancies(V_Ⅰ) and undercoordinated Pb^(2+),limit the performance of perovskite solar cells(PVSCs).To address the issue,1-butyl-3-methylimidazolium trifluoro-methane-sulfonate(BMIMOTF) and its iodide counterpart(BMIMI) are utilized to modify the perovskite surface respectively.We find that BMIMI can change the perovskite surface,whereas BMIMOTF shows a nondestructive and more effective defect passivation,giving significantly reduced defect density and suppressed charge-carrier nonradiative recombination.This mainly attributes to the marked passivation efficacy of OTF-anion on V_Ⅰ and undercoordinated Pb^(2+),rather than BMIMI^(+) cation.Benefiting from the rational surface-modification of BMMIMOTF,the films exhibit an optimized energy level alignment,enhanced hydrophobicity and suppressed ion migration.Consequently,the BMIMOTF-modified devices achieve an impressive efficiency of 21.38% with a record open-circuit voltage of 1.195 V,which is among the best efficiencies reported for 2D PVSCs,and display greatly enhanced humidity and thermal stability.
基金Project supported by the World Academy of Science(TWAS)research grant 2018(Ref:18-121 RG/PHYS/AS I-FR3240303643)North South University(NSU),Bangladesh,internal research grant 2018-19&2019-20(approved by the members of BOT,NSU,Bangladesh)
文摘Considering the inhomogeneous or heterogeneous background, we have demonstrated that if the background and the half-immersed object are both non-absorbing, the transferred photon momentum to the pulled object can be considered as the one of Minkowski exactly at the interface. In contrast, the presence of loss inside matter, either in the half-immersed object or in the background, causes optical pushing of the object. Our analysis suggests that for half-immersed plasmonic or lossy dielectric, the transferred momentum of photon can mathematically be modeled as the type of Minkowski and also of Abraham. However, according to a final critical analysis, the idea of Abraham momentum transfer has been rejected. Hence,an obvious question arises: whence the Abraham momentum? It is demonstrated that though the transferred momentum to a half-immersed Mie object(lossy or lossless) can better be considered as the Minkowski momentum, Lorentz force analysis suggests that the momentum of a photon traveling through the continuous background, however, can be modeled as the type of Abraham. Finally, as an interesting sidewalk, a machine learning based system has been developed to predict the time-averaged force within a very short time avoiding time-consuming full wave simulation.
基金Tsupported by the Science and Technology Development Project of Henan Province(grant no.202300410048)the Intelligence Introduction Plan of Henan Province in 2021(CXJD2021008)+3 种基金the Postdoctoral Fund of China(grant no.FJ3050A0670111)the Henan University Fundthe Canada Research Chairs Supplement FundNew Frontiers in Research Fund(NFRF)。
文摘A photovoltaic technology historically goes through two major steps to evolve into a mature technology. The first step involves advances in materials and is usually accompanied by the rapid improvement of power conversion efficiency. The second step focuses on interfaces and is usually accompanied by significant stability improvement. As an emerging generation of photovoltaic technology, perovskite solar cells are transitioning to the second step of their development when a significant focus shifts toward interface studies and engineering. While various interface engineering strategies have been developed, interfacial characterization is crucial to show the effectiveness of interfacial modification. Here, we review the characterization techniques that have been utilized in studying interface properties in perovskite solar cells. We first summarize the main roles of interfaces in perovskite solar cells, and then we discuss some typical characterization methodologies for morphological, optical,and electrical studies of interfaces. Successful experiences and existing problems are analyzed when discussing some commonly used methods. We then analyze the challenges and provide an outlook for further development of interfacial characterizations. This review aims to evoke strengthened research devotion on novel and persuasive interfacial engineering.
基金This work is supported by the National Science Foundation under Award OIA-1757207.
文摘In order to accommodate the large number of Internet of Things(IoT)connections in mobile networks,Non-Orthogonal Multiple Access(NOMA)has been applied as the resource sharing mechanism in mobile access networks to improve the spectrum efficiency.The NOMA-based resource management for uplink communications comprises two problems,i.e.,user clustering and power&wireless channel allocation.User clustering refers to assigning users in terms of IoT devices to different clusters(where users in the same cluster are sharing the wireless channels to upload their data),and power&wireless channel allocation is to optimize the transmission power of the users and the number of wireless channels allocated to the users in a cluster.The two problems are coupled together,thus making it difficult to solve the NOMA-based resource management problem.In this paper,we propose a QoS-aWarE resourcE managemenT(SWEET)for NOMA algorithm to jointly optimize the user clustering,power management,and wireless channel allocation such that the number of wireless channels is minimized and the data rate requirements of the users can be satisfied.The performance of SWEET is validated via extensive simulations.
基金supported in part by United States Air Force Research Institute for Tactical Autonomy(RITA)University Affiliated Research Center(UARC)in part by the United States Air Force Office of Scientific Research(AFOSR)Contract FA9550-22-1-0268 awarded to KHA,https://www.afrl.af.mil/AFOSR/The contract is entitled:“Investigating Improving Safety of Autonomous Exploring Intelligent Agents with Human-in-the-Loop Reinforcement Learning,”and in part by Jackson State University.
文摘Multi-Agent Reinforcement Learning(MARL)has proven to be successful in cooperative assignments.MARL is used to investigate how autonomous agents with the same interests can connect and act in one team.MARL cooperation scenarios are explored in recreational cooperative augmented reality environments,as well as realworld scenarios in robotics.In this paper,we explore the realm of MARL and its potential applications in cooperative assignments.Our focus is on developing a multi-agent system that can collaborate to attack or defend against enemies and achieve victory withminimal damage.To accomplish this,we utilize the StarCraftMulti-Agent Challenge(SMAC)environment and train four MARL algorithms:Q-learning with Mixtures of Experts(QMIX),Value-DecompositionNetwork(VDN),Multi-agent Proximal PolicyOptimizer(MAPPO),andMulti-Agent Actor Attention Critic(MAA2C).These algorithms allow multiple agents to cooperate in a specific scenario to achieve the targeted mission.Our results show that the QMIX algorithm outperforms the other three algorithms in the attacking scenario,while the VDN algorithm achieves the best results in the defending scenario.Specifically,the VDNalgorithmreaches the highest value of battle wonmean and the lowest value of dead alliesmean.Our research demonstrates the potential forMARL algorithms to be used in real-world applications,such as controllingmultiple robots to provide helpful services or coordinating teams of agents to accomplish tasks that would be impossible for a human to do.The SMAC environment provides a unique opportunity to test and evaluate MARL algorithms in a challenging and dynamic environment,and our results show that these algorithms can be used to achieve victory with minimal damage.
基金National Natural Science Foundation of China(12072189,82171011)Shanghai Jiao Tong University‘Deep Blue Program’Fund(Grant No.SL2103)+1 种基金Project of Biobank(No.YBKB202117)from Shanghai Ninth People’s HospitalShanghai Jiao Tong University School of Medicine and Science Foundation of National Key Laboratory of Science and Technology on Advanced Composites in Special Environments(No.6142905223704)。
文摘Piezoelectric ultrasonic transducers have shown great potential in biomedical applications due to their high acoustic-to-electric conversion efficiency and large power capacity.The focusing technique enables the transducer to produce an extremely narrow beam,greatly improving the resolution and sensitivity.In this work,we summarize the fundamental properties and biological effects of the ultrasound field,aiming to establish a correlation between device design and application.Focusing techniques for piezoelectric transducers are highlighted,including material selection and fabrication methods,which determine the final performance of piezoelectric transducers.Numerous examples,from ultrasound imaging,neuromodulation,tumor ablation to ultrasonic wireless energy transfer,are summarized to highlight the great promise of biomedical applications.Finally,the challenges and opportunities of focused ultrasound transducers are presented.The aim of this review is to bridge the gap between focused ultrasound systems and biomedical applications.
