This paper develops a variational model for image noise removal using total curvature(TC), which is a high-order regularizer. The TC has the advantage of preserving image feature. Unfortunately, it also has the charac...This paper develops a variational model for image noise removal using total curvature(TC), which is a high-order regularizer. The TC has the advantage of preserving image feature. Unfortunately, it also has the characteristics of nonlinear, non-convex and non-smooth. Consequently, the numerical computation with the curvature regularization is difficult. In order to conquer the computation problem, the proposed model is transformed into an alternating optimization problem by importing auxiliary variables. Furthermore, based on alternating direction method of multipliers, we design a fast numerical approximation iterative scheme for proposed model. Finally, numerous experiments are implemented to indicate the advantages of the proposed model in image edge preserving, image contrast and corners preserving. Meanwhile, the high computational efficiency of the designed model is verified by comparing with traditional models, including the total variation(TV) and total Laplace(TL) model.展开更多
【目的】在空间超冗余机械臂动力学建模中,其结构复杂、自由度多及刚性弱导致的动力学耦合问题十分突出,难以获得精准的动力学模型。针对此问题,提出了一种应用迭代WLS-TCS算法的空间超冗余机械臂地面动力学参数辨识方法,为获取机械臂...【目的】在空间超冗余机械臂动力学建模中,其结构复杂、自由度多及刚性弱导致的动力学耦合问题十分突出,难以获得精准的动力学模型。针对此问题,提出了一种应用迭代WLS-TCS算法的空间超冗余机械臂地面动力学参数辨识方法,为获取机械臂的高精度动力学模型和空间在轨动力学控制研究奠定基础。【方法】首先,采用一种基于终端交叉和转向的粒子群优化(Terminal Crossover and Steering-based Particle Swarm Optimization,TCS-PSO)算法来设计满足多约束条件的周期傅里叶级数,并将其作为最优的激励轨迹;其次,应用迭代加权最小二乘(Iterative Weighted Least Squares,IWLS)法获取最小参数集,通过迭代加权逐步剔除数据中的异常值,使得辨识结果更加鲁棒、准确。【结果】试验结果表明,在激励轨迹中,采用TCS优化方法获得的轨迹回归矩阵条件数更少,且能更好满足所给的约束条件。在参数辨识中,采用IWLS法辨识所得的结果对比递归最小二乘法,力矩残差均方根(Root Mean Square,RMS)值平均降低约2.22%;对比加权最小二乘法,力矩残差RMS值平均降低约4.85%。将获取的参数模型代入到零力控制试验中,实际效果符合预期。展开更多
By analyzing the internal features of counting sorting algorithm. Two improvements of counting sorting algorithms are proposed, which have a wide range of applications and better efficiency than the original counting ...By analyzing the internal features of counting sorting algorithm. Two improvements of counting sorting algorithms are proposed, which have a wide range of applications and better efficiency than the original counting sort while maintaining the original stability. Compared with the original counting sort, it has a wider scope of application and better time and space efficiency. In addition, the accuracy of the above conclusions can be proved by a large amount of experimental data.展开更多
鱼群多目标准确计数是水生态智能监测和集约化养殖产业中的重要环节,对水域生态环境智能保护和水产养殖现代化具有重要作用。现有鱼群多目标准确追踪和计数方法主要适用于鱼群外观清晰、游速缓慢和方向稳定等较理想的情况,难以有效适用...鱼群多目标准确计数是水生态智能监测和集约化养殖产业中的重要环节,对水域生态环境智能保护和水产养殖现代化具有重要作用。现有鱼群多目标准确追踪和计数方法主要适用于鱼群外观清晰、游速缓慢和方向稳定等较理想的情况,难以有效适用于现实情况下存在的鱼群互相遮挡、游动迅速和方向多变等复杂情况。为此,结合轻量化目标检测模型YOLOv5n,提出基于水平相似度匹配机制的鱼群追踪与计数方法。将鱼群计数问题视为多目标检测与追踪问题,设计水平相似度匹配机制,并对SORT(Simple Online and Realtime Tracking)算法进行优化。通过高速水流中鱼群个体在帧与帧之间的位置关系对检测框中心点的水平距离进行限制,以有效解决SORT算法存在的目标匹配混乱问题,显著提高追踪效果。实验结果表明,所提方法在鱼群多目标追踪数据集上的性能显著优于现有追踪方法,对目标遮挡、方向变化等情况目标追踪性能提升显著,并且该方法结构简单,易于实际应用。展开更多
This study introduces a hybrid routing protocol,Low Energy Adaptive Clustering Hierarchy—Ant Colony Optimization—Genetic Algorithm(LEACH-ACO-GA),for wireless sensor networks.It combines regional ant colony optimizat...This study introduces a hybrid routing protocol,Low Energy Adaptive Clustering Hierarchy—Ant Colony Optimization—Genetic Algorithm(LEACH-ACO-GA),for wireless sensor networks.It combines regional ant colony optimization for cluster head selection with inter-cluster routing based on a genetic algorithm.The proposed method reduces energy consumption from 6.9 J(LEACH Classic)to 5.6 J(LEACH-ACO-GA)and decreases latency from 460 to 390 ms,while maintaining a packet delivery ratio of 0.97.These values are averaged over 70 rounds based on 30 independent simulation runs conducted on networks with 50 and 200 nodes.The hybrid method extends network lifetime by up to 50%compared to traditional LEACH and improves performance robustness in dense network environments.The results indicate that two-level metaheuristic optimization is effective for scalable and energy-efficient wireless sensor networks in Internet of Things scenarios.展开更多
1 Introduction Estimating the number of triangles in a graph is a fundamental problem and has found applications in many fields.For example,in social network,it can help us understand how closely the local community s...1 Introduction Estimating the number of triangles in a graph is a fundamental problem and has found applications in many fields.For example,in social network,it can help us understand how closely the local community structure and nodes in the network are in close proximity.In this paper,we address this problem in the framework of graph streaming algorithms,which has received significant attention due to the increasing need to analyze large-scale graph data efficiently[1–3].However,most of these algorithms are not robust or are limited to unweighted graphs.展开更多
针对单光子深度成像中探测器受散粒噪声和背景噪声的干扰,以及无人机在飞行过程中姿态变化带来的单轴图像偏差问题,在经典的SPIRAL-TAP重建框架基础上,提出了一种融合多尺度图像特征与自适应阈值筛选的新型深度图重建方法,旨在提升深度...针对单光子深度成像中探测器受散粒噪声和背景噪声的干扰,以及无人机在飞行过程中姿态变化带来的单轴图像偏差问题,在经典的SPIRAL-TAP重建框架基础上,提出了一种融合多尺度图像特征与自适应阈值筛选的新型深度图重建方法,旨在提升深度图像在低信号背景噪声比(SBR)或高信号背景噪声比下的重建质量。该方法首先通过多尺度梯度与局部方差计算生成图像加权矩阵,以刻画图像纹理复杂度;随后结合基于ROM(Rough Order Map)估计的尺度因子对阈值进行动态调整,以增强噪声鲁棒性;在阈值筛选阶段,提出自适应阈值策略,将尺度平滑与加权矩阵软调融合,限制阈值范围,使筛选更加稳定可靠。实验结果表明,在多种SBR和光子强度条件下,并考虑到无人机单轴姿态偏差影响下,本文方法均优于传统SPIRAL-TAP算法,具有更低的RMSE误差和更好的重建质量。在倾斜角为10°和15°时RMSE分别由0.32降至0.14和从0.43降至0.21。本文方法为无人机载单光子深度图像重建提供了有效的新思路,未来可用在机载高速单光子成像系统中。展开更多
Sustained heavy ethanol drinking is a common problem globally and ethanol is one of the most abused drugs among individuals of different socio-economic status including the HIV-infected patients on antiretroviral drug...Sustained heavy ethanol drinking is a common problem globally and ethanol is one of the most abused drugs among individuals of different socio-economic status including the HIV-infected patients on antiretroviral drugs. Ethanol is reward drug and a CNS depressant especially at high doses. The study determined the effect of sustained heavy ethanol drinking by HIV-infected patients on d4T/3TC/NVP regimen on CD4+ cell counts in Uganda using WHO AUDIT tool and chronic alcohol-use biomarkers. A case control study using repeated measures design with serial measurements model was used. The patients on stavudine (d4T) 30 mg, lamivudine (3TC) 150 mg and nevirapine (NVP) 200 mg and chronic alcohol use were recruited. A total of 41 patients (20 in alcohol group and 21 in control group) were screened for chronic alcohol use by WHO AUDIT tool and chronic alcohol use biomarkers. They were followed up for 9 months with blood sampling done at 3 months intervals. CD4+ cell count was determined using Facscalibur Flow Cytometer system. Results were then sorted by alcohol-use biomarkers (GGT, MCV and AST/ ALT ratio). Data were analysed using SAS 2003 version 9.1 statistical package with repeated measures fixed model and the means were compared using student t-test. The mean CD4+ cell counts in all the groups were lower than the reference ranges at baseline and gradually increased at 3, 6 and 9 months of follow-up. The mean CD4+ cell counts were higher in the control group as compared to the chronic alcohol use group in both WHO AUDIT tool group and chronic alcohol-use biomarkers group though there was no significant difference (p > 0.05). Chronic alcohol use slightly lowers CD4+ cell count in HIV-infected patients on d4T/3TC/NVP treatment regimen.展开更多
驱动力控制系统(Traction Control System,TCS)是在制动防抱死系统的基础上发展起来的一套主动安全控制系统,它根据汽车的行驶状况,通过采用适当的控制算法使汽车驱动轮在恶劣路面或复杂行驶条件下也能产生最佳的纵向驱动力,从而提高汽...驱动力控制系统(Traction Control System,TCS)是在制动防抱死系统的基础上发展起来的一套主动安全控制系统,它根据汽车的行驶状况,通过采用适当的控制算法使汽车驱动轮在恶劣路面或复杂行驶条件下也能产生最佳的纵向驱动力,从而提高汽车的驱动性能和行驶稳定安全性能。通过对TCS控制原理的分析,明确滑转率的控制目标,结合TCS的控制方式,阐述TCS的常用控制算法,并对其进行比较,探讨TCS控制算法的选择依据和方法。展开更多
Regression testing(RT)is an essential but an expensive activity in software development.RT confirms that new faults/errors will not have occurred in the modified program.RT efficiency can be improved through an effect...Regression testing(RT)is an essential but an expensive activity in software development.RT confirms that new faults/errors will not have occurred in the modified program.RT efficiency can be improved through an effective technique of selected only modified test cases that appropriate to the modifications within the given time frame.Earlier,several test case selection approaches have been introduced,but either these techniques were not sufficient according to the requirements of software tester experts or they are ineffective and cannot be used for available test suite specifications and architecture.To address these limitations,we recommend an improved and efficient test case selection(TCS)algorithm for RT.Our proposed technique decreases the execution time and redundancy of the duplicate test cases(TC)and detects onlymodified changes that appropriate to themodifications in test cases.To reduce execution time for TCS,evaluation results of our proposed approach are established on fault detection,redundancy and already executed test case.Results indicate that proposed technique decreases the inclusive testing time of TCS to execute modified test cases by,on average related to a method of Hybrid Whale Algorithm(HWOA),which is a progressive TCS approach in regression testing for a single product.展开更多
Deep learning-based intelligent recognition algorithms are increasingly recognized for their potential to address the labor-intensive challenge of manual pest detection.However,their deployment on mobile devices has b...Deep learning-based intelligent recognition algorithms are increasingly recognized for their potential to address the labor-intensive challenge of manual pest detection.However,their deployment on mobile devices has been constrained by high computational demands.Here,we developed GBiDC-PEST,a mobile application that incorporates an improved,lightweight detection algorithm based on the You Only Look Once(YOLO)series singlestage architecture,for real-time detection of four tiny pests(wheat mites,sugarcane aphids,wheat aphids,and rice planthoppers).GBiDC-PEST incorporates several innovative modules,including GhostNet for lightweight feature extraction and architecture optimization by reconstructing the backbone,the bi-directional feature pyramid network(BiFPN)for enhanced multiscale feature fusion,depthwise convolution(DWConv)layers to reduce computational load,and the convolutional block attention module(CBAM)to enable precise feature focus.The newly developed GBiDC-PEST was trained and validated using a multitarget agricultural tiny pest dataset(Tpest-3960)that covered various field environments.GBiDC-PEST(2.8 MB)significantly reduced the model size to only 20%of the original model size,offering a smaller size than the YOLO series(v5-v10),higher detection accuracy than YOLOv10n and v10s,and faster detection speed than v8s,v9c,v10m and v10b.In Android deployment experiments,GBiDCPEST demonstrated enhanced performance in detecting pests against complex backgrounds,and the accuracy for wheat mites and rice planthoppers was improved by 4.5-7.5%compared with the original model.The GBiDC-PEST optimization algorithm and its mobile deployment proposed in this study offer a robust technical framework for the rapid,onsite identification and localization of tiny pests.This advancement provides valuable insights for effective pest monitoring,counting,and control in various agricultural settings.展开更多
在平抑光伏功率波动过程中,电池储能系统(battery energy storage system,BESS)因保持持续充、放电状态而导致寿命损耗较大。基于电池分组控制技术,提出考虑寿命延长的BESS平抑光伏分组功率分配办法。设计了食肉植物算法优化的改进雨流...在平抑光伏功率波动过程中,电池储能系统(battery energy storage system,BESS)因保持持续充、放电状态而导致寿命损耗较大。基于电池分组控制技术,提出考虑寿命延长的BESS平抑光伏分组功率分配办法。设计了食肉植物算法优化的改进雨流计数法,以获取光伏并网功率指令;利用小波包分解确定电池组数量及容量,同时根据设计的充、放电原则形成电池组的功率调节指令;进行电池组组别重置时,将BESS中诸多电池单元进行有序分配;提出二次功率分配策略,获取各电池单元的功率调节指令,二次分配时还应用了重复补发原则以最大限度跟踪功率调节指令,并保证组内电池单元荷电状态均衡。对所提功率分配方法进行了仿真验证,并与其他5种策略进行了对比,结果表明,所提功率分配方法实现了BESS对于功率调节指令的更好跟踪,降低了光伏并网功率波动率,延长了电池单元的使用寿命。展开更多
基金supported by the National Natural Science Foundation of China(No.61602269)the China Postdoctoral Science Foundation(No.2015M571993)+1 种基金the Shandong Provincial Natural Science Foundation of China(No.ZR2017MD004)the Qingdao Postdoctoral Application Research Funded Project
摘要This paper develops a variational model for image noise removal using total curvature(TC), which is a high-order regularizer. The TC has the advantage of preserving image feature. Unfortunately, it also has the characteristics of nonlinear, non-convex and non-smooth. Consequently, the numerical computation with the curvature regularization is difficult. In order to conquer the computation problem, the proposed model is transformed into an alternating optimization problem by importing auxiliary variables. Furthermore, based on alternating direction method of multipliers, we design a fast numerical approximation iterative scheme for proposed model. Finally, numerous experiments are implemented to indicate the advantages of the proposed model in image edge preserving, image contrast and corners preserving. Meanwhile, the high computational efficiency of the designed model is verified by comparing with traditional models, including the total variation(TV) and total Laplace(TL) model.
摘要【目的】在空间超冗余机械臂动力学建模中,其结构复杂、自由度多及刚性弱导致的动力学耦合问题十分突出,难以获得精准的动力学模型。针对此问题,提出了一种应用迭代WLS-TCS算法的空间超冗余机械臂地面动力学参数辨识方法,为获取机械臂的高精度动力学模型和空间在轨动力学控制研究奠定基础。【方法】首先,采用一种基于终端交叉和转向的粒子群优化(Terminal Crossover and Steering-based Particle Swarm Optimization,TCS-PSO)算法来设计满足多约束条件的周期傅里叶级数,并将其作为最优的激励轨迹;其次,应用迭代加权最小二乘(Iterative Weighted Least Squares,IWLS)法获取最小参数集,通过迭代加权逐步剔除数据中的异常值,使得辨识结果更加鲁棒、准确。【结果】试验结果表明,在激励轨迹中,采用TCS优化方法获得的轨迹回归矩阵条件数更少,且能更好满足所给的约束条件。在参数辨识中,采用IWLS法辨识所得的结果对比递归最小二乘法,力矩残差均方根(Root Mean Square,RMS)值平均降低约2.22%;对比加权最小二乘法,力矩残差RMS值平均降低约4.85%。将获取的参数模型代入到零力控制试验中,实际效果符合预期。
摘要By analyzing the internal features of counting sorting algorithm. Two improvements of counting sorting algorithms are proposed, which have a wide range of applications and better efficiency than the original counting sort while maintaining the original stability. Compared with the original counting sort, it has a wider scope of application and better time and space efficiency. In addition, the accuracy of the above conclusions can be proved by a large amount of experimental data.
摘要鱼群多目标准确计数是水生态智能监测和集约化养殖产业中的重要环节,对水域生态环境智能保护和水产养殖现代化具有重要作用。现有鱼群多目标准确追踪和计数方法主要适用于鱼群外观清晰、游速缓慢和方向稳定等较理想的情况,难以有效适用于现实情况下存在的鱼群互相遮挡、游动迅速和方向多变等复杂情况。为此,结合轻量化目标检测模型YOLOv5n,提出基于水平相似度匹配机制的鱼群追踪与计数方法。将鱼群计数问题视为多目标检测与追踪问题,设计水平相似度匹配机制,并对SORT(Simple Online and Realtime Tracking)算法进行优化。通过高速水流中鱼群个体在帧与帧之间的位置关系对检测框中心点的水平距离进行限制,以有效解决SORT算法存在的目标匹配混乱问题,显著提高追踪效果。实验结果表明,所提方法在鱼群多目标追踪数据集上的性能显著优于现有追踪方法,对目标遮挡、方向变化等情况目标追踪性能提升显著,并且该方法结构简单,易于实际应用。
摘要This study introduces a hybrid routing protocol,Low Energy Adaptive Clustering Hierarchy—Ant Colony Optimization—Genetic Algorithm(LEACH-ACO-GA),for wireless sensor networks.It combines regional ant colony optimization for cluster head selection with inter-cluster routing based on a genetic algorithm.The proposed method reduces energy consumption from 6.9 J(LEACH Classic)to 5.6 J(LEACH-ACO-GA)and decreases latency from 460 to 390 ms,while maintaining a packet delivery ratio of 0.97.These values are averaged over 70 rounds based on 30 independent simulation runs conducted on networks with 50 and 200 nodes.The hybrid method extends network lifetime by up to 50%compared to traditional LEACH and improves performance robustness in dense network environments.The results indicate that two-level metaheuristic optimization is effective for scalable and energy-efficient wireless sensor networks in Internet of Things scenarios.
基金supported in part by the Innovation Program for Quantum Science and Technology(No.2021ZD0302901)in part by the National Natural Science Foundation of China(Grant No.62272431).
摘要1 Introduction Estimating the number of triangles in a graph is a fundamental problem and has found applications in many fields.For example,in social network,it can help us understand how closely the local community structure and nodes in the network are in close proximity.In this paper,we address this problem in the framework of graph streaming algorithms,which has received significant attention due to the increasing need to analyze large-scale graph data efficiently[1–3].However,most of these algorithms are not robust or are limited to unweighted graphs.
摘要针对单光子深度成像中探测器受散粒噪声和背景噪声的干扰,以及无人机在飞行过程中姿态变化带来的单轴图像偏差问题,在经典的SPIRAL-TAP重建框架基础上,提出了一种融合多尺度图像特征与自适应阈值筛选的新型深度图重建方法,旨在提升深度图像在低信号背景噪声比(SBR)或高信号背景噪声比下的重建质量。该方法首先通过多尺度梯度与局部方差计算生成图像加权矩阵,以刻画图像纹理复杂度;随后结合基于ROM(Rough Order Map)估计的尺度因子对阈值进行动态调整,以增强噪声鲁棒性;在阈值筛选阶段,提出自适应阈值策略,将尺度平滑与加权矩阵软调融合,限制阈值范围,使筛选更加稳定可靠。实验结果表明,在多种SBR和光子强度条件下,并考虑到无人机单轴姿态偏差影响下,本文方法均优于传统SPIRAL-TAP算法,具有更低的RMSE误差和更好的重建质量。在倾斜角为10°和15°时RMSE分别由0.32降至0.14和从0.43降至0.21。本文方法为无人机载单光子深度图像重建提供了有效的新思路,未来可用在机载高速单光子成像系统中。
摘要Sustained heavy ethanol drinking is a common problem globally and ethanol is one of the most abused drugs among individuals of different socio-economic status including the HIV-infected patients on antiretroviral drugs. Ethanol is reward drug and a CNS depressant especially at high doses. The study determined the effect of sustained heavy ethanol drinking by HIV-infected patients on d4T/3TC/NVP regimen on CD4+ cell counts in Uganda using WHO AUDIT tool and chronic alcohol-use biomarkers. A case control study using repeated measures design with serial measurements model was used. The patients on stavudine (d4T) 30 mg, lamivudine (3TC) 150 mg and nevirapine (NVP) 200 mg and chronic alcohol use were recruited. A total of 41 patients (20 in alcohol group and 21 in control group) were screened for chronic alcohol use by WHO AUDIT tool and chronic alcohol use biomarkers. They were followed up for 9 months with blood sampling done at 3 months intervals. CD4+ cell count was determined using Facscalibur Flow Cytometer system. Results were then sorted by alcohol-use biomarkers (GGT, MCV and AST/ ALT ratio). Data were analysed using SAS 2003 version 9.1 statistical package with repeated measures fixed model and the means were compared using student t-test. The mean CD4+ cell counts in all the groups were lower than the reference ranges at baseline and gradually increased at 3, 6 and 9 months of follow-up. The mean CD4+ cell counts were higher in the control group as compared to the chronic alcohol use group in both WHO AUDIT tool group and chronic alcohol-use biomarkers group though there was no significant difference (p > 0.05). Chronic alcohol use slightly lowers CD4+ cell count in HIV-infected patients on d4T/3TC/NVP treatment regimen.
摘要驱动力控制系统(Traction Control System,TCS)是在制动防抱死系统的基础上发展起来的一套主动安全控制系统,它根据汽车的行驶状况,通过采用适当的控制算法使汽车驱动轮在恶劣路面或复杂行驶条件下也能产生最佳的纵向驱动力,从而提高汽车的驱动性能和行驶稳定安全性能。通过对TCS控制原理的分析,明确滑转率的控制目标,结合TCS的控制方式,阐述TCS的常用控制算法,并对其进行比较,探讨TCS控制算法的选择依据和方法。
基金This work was supported in part by the Research Management Center(RMC),Universiti Teknologi Malaysia(UTM)and Ministry of Higher Education Malaysia(MOHE)through the UTM High Impact Research(UTMHR)grant scheme under(Vot Number Q.J130000.2451.08G55).
摘要Regression testing(RT)is an essential but an expensive activity in software development.RT confirms that new faults/errors will not have occurred in the modified program.RT efficiency can be improved through an effective technique of selected only modified test cases that appropriate to the modifications within the given time frame.Earlier,several test case selection approaches have been introduced,but either these techniques were not sufficient according to the requirements of software tester experts or they are ineffective and cannot be used for available test suite specifications and architecture.To address these limitations,we recommend an improved and efficient test case selection(TCS)algorithm for RT.Our proposed technique decreases the execution time and redundancy of the duplicate test cases(TC)and detects onlymodified changes that appropriate to themodifications in test cases.To reduce execution time for TCS,evaluation results of our proposed approach are established on fault detection,redundancy and already executed test case.Results indicate that proposed technique decreases the inclusive testing time of TCS to execute modified test cases by,on average related to a method of Hybrid Whale Algorithm(HWOA),which is a progressive TCS approach in regression testing for a single product.
基金support of the Natural Science Foundation of Jiangsu Province,China(BK20240977)the China Scholarship Council(201606850024)+1 种基金the National High Technology Research and Development Program of China(2016YFD0701003)the Postgraduate Research&Practice Innovation Program of Jiangsu Province,China(SJCX23_1488)。
摘要Deep learning-based intelligent recognition algorithms are increasingly recognized for their potential to address the labor-intensive challenge of manual pest detection.However,their deployment on mobile devices has been constrained by high computational demands.Here,we developed GBiDC-PEST,a mobile application that incorporates an improved,lightweight detection algorithm based on the You Only Look Once(YOLO)series singlestage architecture,for real-time detection of four tiny pests(wheat mites,sugarcane aphids,wheat aphids,and rice planthoppers).GBiDC-PEST incorporates several innovative modules,including GhostNet for lightweight feature extraction and architecture optimization by reconstructing the backbone,the bi-directional feature pyramid network(BiFPN)for enhanced multiscale feature fusion,depthwise convolution(DWConv)layers to reduce computational load,and the convolutional block attention module(CBAM)to enable precise feature focus.The newly developed GBiDC-PEST was trained and validated using a multitarget agricultural tiny pest dataset(Tpest-3960)that covered various field environments.GBiDC-PEST(2.8 MB)significantly reduced the model size to only 20%of the original model size,offering a smaller size than the YOLO series(v5-v10),higher detection accuracy than YOLOv10n and v10s,and faster detection speed than v8s,v9c,v10m and v10b.In Android deployment experiments,GBiDCPEST demonstrated enhanced performance in detecting pests against complex backgrounds,and the accuracy for wheat mites and rice planthoppers was improved by 4.5-7.5%compared with the original model.The GBiDC-PEST optimization algorithm and its mobile deployment proposed in this study offer a robust technical framework for the rapid,onsite identification and localization of tiny pests.This advancement provides valuable insights for effective pest monitoring,counting,and control in various agricultural settings.
摘要在平抑光伏功率波动过程中,电池储能系统(battery energy storage system,BESS)因保持持续充、放电状态而导致寿命损耗较大。基于电池分组控制技术,提出考虑寿命延长的BESS平抑光伏分组功率分配办法。设计了食肉植物算法优化的改进雨流计数法,以获取光伏并网功率指令;利用小波包分解确定电池组数量及容量,同时根据设计的充、放电原则形成电池组的功率调节指令;进行电池组组别重置时,将BESS中诸多电池单元进行有序分配;提出二次功率分配策略,获取各电池单元的功率调节指令,二次分配时还应用了重复补发原则以最大限度跟踪功率调节指令,并保证组内电池单元荷电状态均衡。对所提功率分配方法进行了仿真验证,并与其他5种策略进行了对比,结果表明,所提功率分配方法实现了BESS对于功率调节指令的更好跟踪,降低了光伏并网功率波动率,延长了电池单元的使用寿命。