The Internet of Everything(IoE)coupled with Proactive Artificial Intelligence(AI)-Based Learning Agents(PLAs)through a cloud processing system is an idea that connects all computing resources to the Internet,making it...The Internet of Everything(IoE)coupled with Proactive Artificial Intelligence(AI)-Based Learning Agents(PLAs)through a cloud processing system is an idea that connects all computing resources to the Internet,making it possible for these devices to communicate with one another.Technologies featured in the IoE include embedding,networking,and sensing devices.To achieve the intended results of the IoE and ease life for everyone involved,sensing devices and monitoring systems are linked together.The IoE is used in several contexts,including intelligent cars’protection,navigation,security,and fuel efficiency.The Smart Things Monitoring System(STMS)framework,which has been proposed for early occurrence identification and theft prevention,is discussed in this article.The STMS uses technologies based on the IoE and PLAs to continuously and remotely observe,control,and monitor vehicles.The STMS is familiar with the platform used by the global positioning system;as a result,the STMS can maintain a real-time record of current vehicle positions.This information is utilized to locate the vehicle in an accident or theft.The findings of the STMS system are promising for precisely identifying crashes,evaluating incident severity,and locating vehicles after collisions have occurred.Moreover,we formulate an ad hoc STMS network communication scenario to evaluate the efficacy of data communication by utilizing various network parameters,such as round-trip time(RTT),data packet transmission,data packet reception,and loss.From our experimentation,we obtained an improved communication efficiency for STMS across multiple PLAs compared to the standard greedy routing and traditional AODV approaches.Our framework facilitates adaptable solutions with communication competence by deploying Proactive PLAs in a cloud-connected smart vehicular environment.展开更多
In contemporary society,personal vehicles are indispensable for enhancing everyday convenience,and numerous advanced technological solutions for safe driving are being proposed,including autonomous emergency braking s...In contemporary society,personal vehicles are indispensable for enhancing everyday convenience,and numerous advanced technological solutions for safe driving are being proposed,including autonomous emergency braking systems and lane departure warning systems.However,traditional sensors aimed at preventing incapacitated driving due to drowsiness,alcohol consumption,or sudden health issues often require additional power and may infringe upon driver privacy.A self-powered,nonintrusive motion recording system utilizing a triboelectric nanogenerator with an arch and cantilever structure(AC-TENG)as a sensor to track driver motions is introduced.Motion patterns of users are captured in real time by imaging the waveforms generated by the AC-TENG.To discern the peaks of the AC-TENG waveforms with greater precision and clarity,the roughness of the contact surface is enhanced using the reactive ion etching(RIE)technique,thereby amplifying the voltage by a factor of 2.1.The resulting output power of 2.77 mW and a corresponding power density of 3.08 W/m^(2)are demonstrated.Energy harvesting is facilitated by the proposed AC-TENG sensor,coupled with a power management integrated circuit(PMIC).Additionally,continuous wireless data transmission is enabled by using it as an input source alongside a solar cell.Motion data captured by the sensor are classified via deep transfer learning,enabling real-time monitoring of safe driving.Upon detection of any abnormal signals,the driver is promptly alerted by this system,and its application can be extended to functionalities such as transitioning the vehicle to autonomous driving mode.展开更多
Partial Differential Equations(PDEs)are model candidates of soft sensing for aero-engine health management units.The existing Physics-Informed Neural Networks(PINNs)have made achievements.However,unmeasurable aero-eng...Partial Differential Equations(PDEs)are model candidates of soft sensing for aero-engine health management units.The existing Physics-Informed Neural Networks(PINNs)have made achievements.However,unmeasurable aero-engine driving sources lead to unknown PDE driving terms,which weaken PINNs feasibility.To this end,Physically Informed Hierarchical Learning followed by Recurrent-Prediction Term(PIHL-RPT)is proposed.First,PIHL is proposed for learning nonhomogeneous PDE solutions,in which two networks NetU and NetG are constructed.NetU is for learning solutions satisfying PDEs;NetG is for learning driving terms to regularize NetU training.Then,we propose a hierarchical learning strategy to optimize and couple NetU and NetG,which are integrated into a data-physics-hybrid loss function.Besides,we prove PIHL-RPT can iteratively generate a series of networks converging to a function,which can approximate a solution to well-posed PDE.Furthermore,RPT is proposed for prediction improvement of PIHL,in which network NetU-RP is constructed to compensate for information loss caused by data sampling and driving sources’immeasurability.Finally,artificial datasets and practical vibration process datasets from our wear experiment platform are used to verify the feasibility and effectiveness of PIHL-RPT based soft sensing.Meanwhile,comparisons with relevant methods,discussions,and PIHL-RPT based health monitoring example are given.展开更多
基金funded by the Ministry of Science and Technology,Taiwan,grant number(MOST 111-2221-E167-025-MY2).
文摘The Internet of Everything(IoE)coupled with Proactive Artificial Intelligence(AI)-Based Learning Agents(PLAs)through a cloud processing system is an idea that connects all computing resources to the Internet,making it possible for these devices to communicate with one another.Technologies featured in the IoE include embedding,networking,and sensing devices.To achieve the intended results of the IoE and ease life for everyone involved,sensing devices and monitoring systems are linked together.The IoE is used in several contexts,including intelligent cars’protection,navigation,security,and fuel efficiency.The Smart Things Monitoring System(STMS)framework,which has been proposed for early occurrence identification and theft prevention,is discussed in this article.The STMS uses technologies based on the IoE and PLAs to continuously and remotely observe,control,and monitor vehicles.The STMS is familiar with the platform used by the global positioning system;as a result,the STMS can maintain a real-time record of current vehicle positions.This information is utilized to locate the vehicle in an accident or theft.The findings of the STMS system are promising for precisely identifying crashes,evaluating incident severity,and locating vehicles after collisions have occurred.Moreover,we formulate an ad hoc STMS network communication scenario to evaluate the efficacy of data communication by utilizing various network parameters,such as round-trip time(RTT),data packet transmission,data packet reception,and loss.From our experimentation,we obtained an improved communication efficiency for STMS across multiple PLAs compared to the standard greedy routing and traditional AODV approaches.Our framework facilitates adaptable solutions with communication competence by deploying Proactive PLAs in a cloud-connected smart vehicular environment.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.RS-2024-00357072)the NRF and the Commercialization Promotion Agency for R&D Outcomes(COMPA)grant funded by the Korea government(Ministry of Science and ICT)(No.RS-2024-00432221)+1 种基金the Technology Innovation Program(No.RS-2022-00154983,Development of Low-Power Sensors and Self-Charging Power Sources for Self-Sustainable Wireless Sensor Platforms)funded by the Ministry of Trade,Industry&Energy(MI,Korea)supported by Basic Science Research Program through the NRF funded by the Ministry of Education(No.2018R1A6A1A03025708).
文摘In contemporary society,personal vehicles are indispensable for enhancing everyday convenience,and numerous advanced technological solutions for safe driving are being proposed,including autonomous emergency braking systems and lane departure warning systems.However,traditional sensors aimed at preventing incapacitated driving due to drowsiness,alcohol consumption,or sudden health issues often require additional power and may infringe upon driver privacy.A self-powered,nonintrusive motion recording system utilizing a triboelectric nanogenerator with an arch and cantilever structure(AC-TENG)as a sensor to track driver motions is introduced.Motion patterns of users are captured in real time by imaging the waveforms generated by the AC-TENG.To discern the peaks of the AC-TENG waveforms with greater precision and clarity,the roughness of the contact surface is enhanced using the reactive ion etching(RIE)technique,thereby amplifying the voltage by a factor of 2.1.The resulting output power of 2.77 mW and a corresponding power density of 3.08 W/m^(2)are demonstrated.Energy harvesting is facilitated by the proposed AC-TENG sensor,coupled with a power management integrated circuit(PMIC).Additionally,continuous wireless data transmission is enabled by using it as an input source alongside a solar cell.Motion data captured by the sensor are classified via deep transfer learning,enabling real-time monitoring of safe driving.Upon detection of any abnormal signals,the driver is promptly alerted by this system,and its application can be extended to functionalities such as transitioning the vehicle to autonomous driving mode.
基金supported in part by the National Science and Technology Major Project of China(No.2019-I-0019-0018)the National Natural Science Foundation of China(Nos.61890920,61890921,12302065 and 12172073).
文摘Partial Differential Equations(PDEs)are model candidates of soft sensing for aero-engine health management units.The existing Physics-Informed Neural Networks(PINNs)have made achievements.However,unmeasurable aero-engine driving sources lead to unknown PDE driving terms,which weaken PINNs feasibility.To this end,Physically Informed Hierarchical Learning followed by Recurrent-Prediction Term(PIHL-RPT)is proposed.First,PIHL is proposed for learning nonhomogeneous PDE solutions,in which two networks NetU and NetG are constructed.NetU is for learning solutions satisfying PDEs;NetG is for learning driving terms to regularize NetU training.Then,we propose a hierarchical learning strategy to optimize and couple NetU and NetG,which are integrated into a data-physics-hybrid loss function.Besides,we prove PIHL-RPT can iteratively generate a series of networks converging to a function,which can approximate a solution to well-posed PDE.Furthermore,RPT is proposed for prediction improvement of PIHL,in which network NetU-RP is constructed to compensate for information loss caused by data sampling and driving sources’immeasurability.Finally,artificial datasets and practical vibration process datasets from our wear experiment platform are used to verify the feasibility and effectiveness of PIHL-RPT based soft sensing.Meanwhile,comparisons with relevant methods,discussions,and PIHL-RPT based health monitoring example are given.
