Improving the response of sensors is often hindered by inadequate molding effects and complex manufacturing processes. Here, combining a simple magnetic-field-orientation and nano-imprinting process, a micropillar arr...Improving the response of sensors is often hindered by inadequate molding effects and complex manufacturing processes. Here, combining a simple magnetic-field-orientation and nano-imprinting process, a micropillar arrayed sensor was successfully fabricated, meanwhile, the boron nitride nanosheets (BNNS) were oriented in the polymer matrix. Due to the strain confinement effect, the outputted voltage of m-BNNS/PDMS composite film (SABNNS) demonstrated an improvement of 115.5% compared to the film sample with randomly dispersed nanoparticles. And the device showed a high sensitivity and rapid response capability to human motion. Furthermore, the oriented arrangement of m-BNNS and the enlarged heat dis-sipation area of the micropillar array contribute to the optimized thermal conductivity of the device.展开更多
The effective and timely diagnosis and treatment of ocular diseases are key to the rapid recovery of patients.Today,the mass disease that needs attention in this context is cataracts.Although deep learning has signifi...The effective and timely diagnosis and treatment of ocular diseases are key to the rapid recovery of patients.Today,the mass disease that needs attention in this context is cataracts.Although deep learning has significantly advanced the analysis of ocular disease images,there is a need for a probabilistic model to generate the distributions of potential outcomes and thusmake decisions related to uncertainty quantification.Therefore,this study implements a Bayesian Convolutional Neural Networks(BCNN)model for predicting cataracts by assigning probability values to the predictions.It prepares convolutional neural network(CNN)and BCNN models.The proposed BCNN model is CNN-based in which reparameterization is in the first and last layers of the CNN model.This study then trains them on a dataset of cataract images filtered from the ocular disease fundus images fromKaggle.The deep CNN model has an accuracy of 95%,while the BCNN model has an accuracy of 93.75% along with information on uncertainty estimation of cataracts and normal eye conditions.When compared with other methods,the proposed work reveals that it can be a promising solution for cataract prediction with uncertainty estimation.展开更多
With the rapid advancement of robotics and Artificial Intelligence(AI),aerobics training companion robots now support eco-friendly fitness by reducing reliance on nonrenewable energy.This study presents a solar-powere...With the rapid advancement of robotics and Artificial Intelligence(AI),aerobics training companion robots now support eco-friendly fitness by reducing reliance on nonrenewable energy.This study presents a solar-powered aerobics training robot featuring an adaptive energy management system designed for sustainability and efficiency.The robot integrates machine vision with an enhanced Dynamic Cheetah Optimizer and Bayesian Neural Network(DynCO-BNN)to enable precise exercise monitoring and real-time feedback.Solar tracking technology ensures optimal energy absorption,while a microcontroller-based regulator manages power distribution and robotic movement.Dual-battery switching ensures uninterrupted operation,aided by light and I/V sensors for energy optimization.Using the INSIGHT-LME IMU dataset,which includes motion data from 76 individuals performing Local Muscular Endurance(LME)exercises,the system detects activities,counts repetitions,and recognizes human movements.To minimize energy use during data processing,Min-Max normalization and two-dimensional Discrete Fourier Transform(2D-DFT)are applied,boosting computational efficiency.The robot accurately identifies upper and lower limb movements,delivering effective exercise guidance.The DynCO-BNN model achieved a high tracking accuracy of 96.8%.Results confirm improved solar utilization,ecological sustainability,and reduced dependence on fossil fuels—positioning the robot as a smart,energy-efficient solution for next-generation fitness technology.展开更多
Integrating Tiny Machine Learning(TinyML)with edge computing in remotely sensed images enhances the capabilities of road anomaly detection on a broader level.Constrained devices efficiently implement a Binary Neural N...Integrating Tiny Machine Learning(TinyML)with edge computing in remotely sensed images enhances the capabilities of road anomaly detection on a broader level.Constrained devices efficiently implement a Binary Neural Network(BNN)for road feature extraction,utilizing quantization and compression through a pruning strategy.The modifications resulted in a 28-fold decrease in memory usage and a 25%enhancement in inference speed while only experiencing a 2.5%decrease in accuracy.It showcases its superiority over conventional detection algorithms in different road image scenarios.Although constrained by computer resources and training datasets,our results indicate opportunities for future research,demonstrating that quantization and focused optimization can significantly improve machine learning models’accuracy and operational efficiency.ARM Cortex-M0 gives practical feasibility and substantial benefits while deploying our optimized BNN model on this low-power device:Advanced machine learning in edge computing.The analysis work delves into the educational significance of TinyML and its essential function in analyzing road networks using remote sensing,suggesting ways to improve smart city frameworks in road network assessment,traffic management,and autonomous vehicle navigation systems by emphasizing the importance of new technologies for maintaining and safeguarding road networks.展开更多
A higher value of the dielectric constant of h-BN makes it quite favourable material in energy storing device. The variation in dielectric constant was observed as a function of thickness. In this research work multil...A higher value of the dielectric constant of h-BN makes it quite favourable material in energy storing device. The variation in dielectric constant was observed as a function of thickness. In this research work multilayers of Hexagonal Boron Nitride (h-BN) was fabricated by using the Chemical exfoliation method. Two solvents Dimethylformamide (DMF) and Isopropyl Alcohol (IPA) were used for the exfoliation of h-BN. Successful sonication of hexagonal boron nitride led to the formation of Boron Nitride nanosheets (BNNs). The stable dispersibility of h-BN in Dimethylformamide and Isopropyl Alcohol was confirmed by UV Visible Spectroscopy, X-ray diffraction (XRD) and Scanning electron microscopy (SEM) confirm the mono crystallite structure (002) and nanoflakes like morphology of h-BN respectively. This appropriate strategy offered a feasible route to produce multilayer of hexagonal boron nitride. After the successful fabrication of h-BN multilayers its dielectric properties were calculated by using LCR meter. Profilometer revealed the variation in thickness and value of Dielectric constant was calculated by using its formula.展开更多
Modern rare isotope beam(RIB)factories will significantly enhance the production of extremely rare isotopes(ERI)at or near drip lines.As one of the most important methods employed in RIB factories,the production of ER...Modern rare isotope beam(RIB)factories will significantly enhance the production of extremely rare isotopes(ERI)at or near drip lines.As one of the most important methods employed in RIB factories,the production of ERIs in projectile fragmentation reactions should be theoretically improved to provide better guidance for experimental research.The cross-sections of ERIs produced in 140 MeV/u^(78,86)Kr/^(58,64)Ni/^(40,48)Ca+9Be projectile fragmentation reactions were predicted using the newly proposed models[i.e.,Bayesian neural network(BNN),BNN+FRACS,and FRACS,see Chin.Phys.C,46:074104(2022)]and the frequently used EPAX3 model.With a minimum cross-section of 1015 mb,the possibilities of ERIs discovery in a new facility for rare isotope beams(FRIB)are discussed.展开更多
Tri-flo cyclone,as a dense-medium separation device,is one of the most typical environmentally friendly industrial techniques in the coal washery plants.Surprisingly,no detailed investigation has been conducted to exp...Tri-flo cyclone,as a dense-medium separation device,is one of the most typical environmentally friendly industrial techniques in the coal washery plants.Surprisingly,no detailed investigation has been conducted to explore the effectiveness of tri-flo cyclone operating parameters on their representative metallurgical responses(yield and recovery).To fill this gap,this work for the first time in the coal processing sector is going to introduce a type of advanced intelligent method(boosted-neural network"BNN")which is able to linearly and nonlinearly assess multivariable correlations among all variables,rank them based on their effectiveness and model their produced responses.These assessments and modeling were considered a new concept called"Conscious Laboratory(CL)".CL can markedly decrease the number of laboratory experiments,reduce cost,save time,remove scaling up risks,expand maintaining processes,and significantly improve our knowledge about the modeled system.In this study,a robust monitoring database from the Tabas coal plant was prepared to cover various conditions for building a CL for coal tri-flo separators.Well-known machine learning methods,random forest,and support vector regression were developed to validate BNN outcomes.The comparisons indicated the accuracy and strength of BNN over the examined traditional modeling methods.In a sentence,generating a novel BNN within the CL concept can apply in various energy and coal processing areas,fill gaps in our knowledge about possible interactions,and open a new window for plants’fully automotive process.展开更多
基金supported by the National Natural Science Foundation of China(52175544 and 52172098)the Key R&D Program of Shannxi Province(2022GXLH-01-12,2023-GHZD-11 and 2023QCY-LL-26HZ)the Featured Research Base Project of Xi’an Science and Technology Bureau(23TSPT0001).
文摘Improving the response of sensors is often hindered by inadequate molding effects and complex manufacturing processes. Here, combining a simple magnetic-field-orientation and nano-imprinting process, a micropillar arrayed sensor was successfully fabricated, meanwhile, the boron nitride nanosheets (BNNS) were oriented in the polymer matrix. Due to the strain confinement effect, the outputted voltage of m-BNNS/PDMS composite film (SABNNS) demonstrated an improvement of 115.5% compared to the film sample with randomly dispersed nanoparticles. And the device showed a high sensitivity and rapid response capability to human motion. Furthermore, the oriented arrangement of m-BNNS and the enlarged heat dis-sipation area of the micropillar array contribute to the optimized thermal conductivity of the device.
基金Saudi Arabia for funding this work through Small Research Group Project under Grant Number RGP.1/316/45.
文摘The effective and timely diagnosis and treatment of ocular diseases are key to the rapid recovery of patients.Today,the mass disease that needs attention in this context is cataracts.Although deep learning has significantly advanced the analysis of ocular disease images,there is a need for a probabilistic model to generate the distributions of potential outcomes and thusmake decisions related to uncertainty quantification.Therefore,this study implements a Bayesian Convolutional Neural Networks(BCNN)model for predicting cataracts by assigning probability values to the predictions.It prepares convolutional neural network(CNN)and BCNN models.The proposed BCNN model is CNN-based in which reparameterization is in the first and last layers of the CNN model.This study then trains them on a dataset of cataract images filtered from the ocular disease fundus images fromKaggle.The deep CNN model has an accuracy of 95%,while the BCNN model has an accuracy of 93.75% along with information on uncertainty estimation of cataracts and normal eye conditions.When compared with other methods,the proposed work reveals that it can be a promising solution for cataract prediction with uncertainty estimation.
文摘With the rapid advancement of robotics and Artificial Intelligence(AI),aerobics training companion robots now support eco-friendly fitness by reducing reliance on nonrenewable energy.This study presents a solar-powered aerobics training robot featuring an adaptive energy management system designed for sustainability and efficiency.The robot integrates machine vision with an enhanced Dynamic Cheetah Optimizer and Bayesian Neural Network(DynCO-BNN)to enable precise exercise monitoring and real-time feedback.Solar tracking technology ensures optimal energy absorption,while a microcontroller-based regulator manages power distribution and robotic movement.Dual-battery switching ensures uninterrupted operation,aided by light and I/V sensors for energy optimization.Using the INSIGHT-LME IMU dataset,which includes motion data from 76 individuals performing Local Muscular Endurance(LME)exercises,the system detects activities,counts repetitions,and recognizes human movements.To minimize energy use during data processing,Min-Max normalization and two-dimensional Discrete Fourier Transform(2D-DFT)are applied,boosting computational efficiency.The robot accurately identifies upper and lower limb movements,delivering effective exercise guidance.The DynCO-BNN model achieved a high tracking accuracy of 96.8%.Results confirm improved solar utilization,ecological sustainability,and reduced dependence on fossil fuels—positioning the robot as a smart,energy-efficient solution for next-generation fitness technology.
基金supported by the National Natural Science Foundation of China(61170147)Scientific Research Project of Zhejiang Provincial Department of Education in China(Y202146796)+2 种基金Natural Science Foundation of Zhejiang Province in China(LTY22F020003)Wenzhou Major Scientific and Technological Innovation Project of China(ZG2021029)Scientific and Technological Projects of Henan Province in China(202102210172).
文摘Integrating Tiny Machine Learning(TinyML)with edge computing in remotely sensed images enhances the capabilities of road anomaly detection on a broader level.Constrained devices efficiently implement a Binary Neural Network(BNN)for road feature extraction,utilizing quantization and compression through a pruning strategy.The modifications resulted in a 28-fold decrease in memory usage and a 25%enhancement in inference speed while only experiencing a 2.5%decrease in accuracy.It showcases its superiority over conventional detection algorithms in different road image scenarios.Although constrained by computer resources and training datasets,our results indicate opportunities for future research,demonstrating that quantization and focused optimization can significantly improve machine learning models’accuracy and operational efficiency.ARM Cortex-M0 gives practical feasibility and substantial benefits while deploying our optimized BNN model on this low-power device:Advanced machine learning in edge computing.The analysis work delves into the educational significance of TinyML and its essential function in analyzing road networks using remote sensing,suggesting ways to improve smart city frameworks in road network assessment,traffic management,and autonomous vehicle navigation systems by emphasizing the importance of new technologies for maintaining and safeguarding road networks.
文摘A higher value of the dielectric constant of h-BN makes it quite favourable material in energy storing device. The variation in dielectric constant was observed as a function of thickness. In this research work multilayers of Hexagonal Boron Nitride (h-BN) was fabricated by using the Chemical exfoliation method. Two solvents Dimethylformamide (DMF) and Isopropyl Alcohol (IPA) were used for the exfoliation of h-BN. Successful sonication of hexagonal boron nitride led to the formation of Boron Nitride nanosheets (BNNs). The stable dispersibility of h-BN in Dimethylformamide and Isopropyl Alcohol was confirmed by UV Visible Spectroscopy, X-ray diffraction (XRD) and Scanning electron microscopy (SEM) confirm the mono crystallite structure (002) and nanoflakes like morphology of h-BN respectively. This appropriate strategy offered a feasible route to produce multilayer of hexagonal boron nitride. After the successful fabrication of h-BN multilayers its dielectric properties were calculated by using LCR meter. Profilometer revealed the variation in thickness and value of Dielectric constant was calculated by using its formula.
基金supported by the National Natural Science Foundation of China (No. 11975091)the Program for Innovative Research Team(in Science and Technology) in University of Henan Province,China(No. 21IRTSTHN011)
文摘Modern rare isotope beam(RIB)factories will significantly enhance the production of extremely rare isotopes(ERI)at or near drip lines.As one of the most important methods employed in RIB factories,the production of ERIs in projectile fragmentation reactions should be theoretically improved to provide better guidance for experimental research.The cross-sections of ERIs produced in 140 MeV/u^(78,86)Kr/^(58,64)Ni/^(40,48)Ca+9Be projectile fragmentation reactions were predicted using the newly proposed models[i.e.,Bayesian neural network(BNN),BNN+FRACS,and FRACS,see Chin.Phys.C,46:074104(2022)]and the frequently used EPAX3 model.With a minimum cross-section of 1015 mb,the possibilities of ERIs discovery in a new facility for rare isotope beams(FRIB)are discussed.
文摘Tri-flo cyclone,as a dense-medium separation device,is one of the most typical environmentally friendly industrial techniques in the coal washery plants.Surprisingly,no detailed investigation has been conducted to explore the effectiveness of tri-flo cyclone operating parameters on their representative metallurgical responses(yield and recovery).To fill this gap,this work for the first time in the coal processing sector is going to introduce a type of advanced intelligent method(boosted-neural network"BNN")which is able to linearly and nonlinearly assess multivariable correlations among all variables,rank them based on their effectiveness and model their produced responses.These assessments and modeling were considered a new concept called"Conscious Laboratory(CL)".CL can markedly decrease the number of laboratory experiments,reduce cost,save time,remove scaling up risks,expand maintaining processes,and significantly improve our knowledge about the modeled system.In this study,a robust monitoring database from the Tabas coal plant was prepared to cover various conditions for building a CL for coal tri-flo separators.Well-known machine learning methods,random forest,and support vector regression were developed to validate BNN outcomes.The comparisons indicated the accuracy and strength of BNN over the examined traditional modeling methods.In a sentence,generating a novel BNN within the CL concept can apply in various energy and coal processing areas,fill gaps in our knowledge about possible interactions,and open a new window for plants’fully automotive process.
