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
In unmanned aerial vehicle(UAV)-based scenarios,sensing-aided integrated data and energy networking(IDEN)systems can significantly mitigate non-line-of-sight(NLoS)propagation,thereby enhancing sensing accuracy..Howeve...In unmanned aerial vehicle(UAV)-based scenarios,sensing-aided integrated data and energy networking(IDEN)systems can significantly mitigate non-line-of-sight(NLoS)propagation,thereby enhancing sensing accuracy..However,the rapid channel variations induced by UAV mobility pose a challenge for traditional polar code construction methods,making it difficult to satisfy the stringent requirements of IDEN systems.To address this challenge,we propose a neural network(NN)-based sensing-aided IDEN framework.This system leverages sensing information to assist polar code construction while satisfying energy constraints.Furthermore,it incorporates neural networks to optimize the performance of polar codes in dynamic environments.Specifically,a sensing-aided binarized neural network(BNN)-based polar encoder is proposed for both lowlatency and high-reliability requirements,and a deep neural network(DNN)-based polar decoder is applied to match the encoder.Moreover,the corresponding training method is proposed,which focuses on the initialization design of the NNs.The simulation results show that the NN-based sensing-aided polar encoding scheme outperforms the conventional counterparts in terms of IDEN for both low-latency and high-reliability requirements.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
预测含伪结的RNA分子二级结构是生物信息学的一个研究难点。利用多分类支持向量机结合贝叶斯神经网络针对含伪结的RNA分子二级结构进行预测。利用多分类支持向量机进行预测,输出端得到相应碱基的平面伪结结构的E-NSSEL(Ex-tend New Seco...预测含伪结的RNA分子二级结构是生物信息学的一个研究难点。利用多分类支持向量机结合贝叶斯神经网络针对含伪结的RNA分子二级结构进行预测。利用多分类支持向量机进行预测,输出端得到相应碱基的平面伪结结构的E-NSSEL(Ex-tend New Secondary Structure Element Label)类别标签。使用碱基已预测的结果通过贝叶斯神经网络进行修正,并恢复RNA分子二级结构。使用该方法能有效地改善含伪结的RNA分子二级结构的预测效果。展开更多
Fragment production in spallation reactions yields key infrastructure data for various applications.Based on the empirical SPACS parameterizations,a Bayesian-neural-network(BNN)approach is established to predict the f...Fragment production in spallation reactions yields key infrastructure data for various applications.Based on the empirical SPACS parameterizations,a Bayesian-neural-network(BNN)approach is established to predict the fragment cross sections in proton-induced spallation reactions.A systematic investigation has been performed for the measured proton-induced spallation reactions of systems ranging from intermediate to heavy nuclei systems and incident energies ranging from 168 MeV/u to 1500 MeV/u.By learning the residuals between the experimental measurements and SPACS predictions,it is found that the BNN-predicted results are in good agreement with the measured results.The established method is suggested to benefit the related research on nuclear astrophysics,nuclear radioactive beam sources,accelerator driven systems,proton therapy,etc.展开更多
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.
基金supported in part by the Natural Science Foundation of China under Grants 62132004,62531008,and 62301122in part by Jiangsu Major Project on Fundamental Research under Grant BK20243059+3 种基金in part by Gusu Innovation Project under Grant ZXL2024360in part by the High-Tech District of Suzhou City under Grant RC2025001in part by Quzhou Government under Grants 2024D007,and 2023D005in part by the Xiaomi Young Scholar Award,in part by Nanjing University-China Mobile Communications Group Co.,Ltd.Joint Institute.
文摘In unmanned aerial vehicle(UAV)-based scenarios,sensing-aided integrated data and energy networking(IDEN)systems can significantly mitigate non-line-of-sight(NLoS)propagation,thereby enhancing sensing accuracy..However,the rapid channel variations induced by UAV mobility pose a challenge for traditional polar code construction methods,making it difficult to satisfy the stringent requirements of IDEN systems.To address this challenge,we propose a neural network(NN)-based sensing-aided IDEN framework.This system leverages sensing information to assist polar code construction while satisfying energy constraints.Furthermore,it incorporates neural networks to optimize the performance of polar codes in dynamic environments.Specifically,a sensing-aided binarized neural network(BNN)-based polar encoder is proposed for both lowlatency and high-reliability requirements,and a deep neural network(DNN)-based polar decoder is applied to match the encoder.Moreover,the corresponding training method is proposed,which focuses on the initialization design of the NNs.The simulation results show that the NN-based sensing-aided polar encoding scheme outperforms the conventional counterparts in terms of IDEN for both low-latency and high-reliability requirements.
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.
文摘预测含伪结的RNA分子二级结构是生物信息学的一个研究难点。利用多分类支持向量机结合贝叶斯神经网络针对含伪结的RNA分子二级结构进行预测。利用多分类支持向量机进行预测,输出端得到相应碱基的平面伪结结构的E-NSSEL(Ex-tend New Secondary Structure Element Label)类别标签。使用碱基已预测的结果通过贝叶斯神经网络进行修正,并恢复RNA分子二级结构。使用该方法能有效地改善含伪结的RNA分子二级结构的预测效果。
基金Supported by the National Natural Science Foundation of China(U1732135,11975091)。
文摘Fragment production in spallation reactions yields key infrastructure data for various applications.Based on the empirical SPACS parameterizations,a Bayesian-neural-network(BNN)approach is established to predict the fragment cross sections in proton-induced spallation reactions.A systematic investigation has been performed for the measured proton-induced spallation reactions of systems ranging from intermediate to heavy nuclei systems and incident energies ranging from 168 MeV/u to 1500 MeV/u.By learning the residuals between the experimental measurements and SPACS predictions,it is found that the BNN-predicted results are in good agreement with the measured results.The established method is suggested to benefit the related research on nuclear astrophysics,nuclear radioactive beam sources,accelerator driven systems,proton therapy,etc.
