This study aimed to address the challenge of accurately and reliably detecting tomatoes in dense planting environments,a critical prerequisite for the automation implementation of robotic harvesting.However,the heavy ...This study aimed to address the challenge of accurately and reliably detecting tomatoes in dense planting environments,a critical prerequisite for the automation implementation of robotic harvesting.However,the heavy reliance on extensive manually annotated datasets for training deep learning models still poses significant limitations to their application in real-world agricultural production environments.To overcome these limitations,we employed domain adaptive learning approach combined with the YOLOv5 model to develop a novel tomato detection model called as TDA-YOLO(tomato detection domain adaptation).We designated the normal illumination scenes in dense planting environments as the source domain and utilized various other illumination scenes as the target domain.To construct bridge mechanism between source and target domains,neural preset for color style transfer is introduced to generate a pseudo-dataset,which served to deal with domain discrepancy.Furthermore,this study combines the semi-supervised learning method to enable the model to extract domain-invariant features more fully,and uses knowledge distillation to improve the model's ability to adapt to the target domain.Additionally,for purpose of promoting inference speed and low computational demand,the lightweight FasterNet network was integrated into the YOLOv5's C3 module,creating a modified C3_Faster module.The experimental results demonstrated that the proposed TDA-YOLO model significantly outperformed original YOLOv5s model,achieving a mAP(mean average precision)of 96.80%for tomato detection across diverse scenarios in dense planting environments,increasing by 7.19 percentage points;Compared with the latest YOLOv8 and YOLOv9,it is also 2.17 and 1.19 percentage points higher,respectively.The model's average detection time per image was an impressive 15 milliseconds,with a FLOPs(floating point operations per second)count of 13.8 G.After acceleration processing,the detection accuracy of the TDA-YOLO model on the Jetson Xavier NX development board is 90.95%,the mAP value is 91.35%,and the detection time of each image is 21 ms,which can still meet the requirements of real-time detection of tomatoes in dense planting environment.The experimental results show that the proposed TDA-YOLO model can accurately and quickly detect tomatoes in dense planting environment,and at the same time avoid the use of a large number of annotated data,which provides technical support for the development of automatic harvesting systems for tomatoes and other fruits.展开更多
Because most ensemble learning algorithms use the centralized model, and the training instances must be centralized on a single station, it is difficult to centralize the training data on a station. A distributed ense...Because most ensemble learning algorithms use the centralized model, and the training instances must be centralized on a single station, it is difficult to centralize the training data on a station. A distributed ensemble learning algorithm is proposed which has two kinds of weight genes of instances that denote the global distribution and the local distribution. Instead of the repeated sampling method in the standard ensemble learning, non-balance sampling from each station is used to train the base classifier set of each station. The concept of the effective nearby region for local integration classifier is proposed, and is used for the dynamic integration method of multiple classifiers in distributed environment. The experiments show that the ensemble learning algorithm in distributed environment proposed could reduce the time of training the base classifiers effectively, and ensure the classify performance is as same as the centralized learning method.展开更多
From the viewpoint of psycholinguistics, this paper concerns how to create an optimal language learning environment in language learning, to stimulate students enthusiasm to participate in classroom activities and t...From the viewpoint of psycholinguistics, this paper concerns how to create an optimal language learning environment in language learning, to stimulate students enthusiasm to participate in classroom activities and to make language learning easier and more pleasant.展开更多
The ocean is one of the essential fields of national defense in the future,and more and more attention is paid to the lightweight research of Marine equipment and materials.This study it is to develop a Machine learni...The ocean is one of the essential fields of national defense in the future,and more and more attention is paid to the lightweight research of Marine equipment and materials.This study it is to develop a Machine learning(ML)-based prediction method to study the evolution of the mechanical properties of Al-Li alloys in the marine environment.We obtained the mechanical properties of Al-Li alloy samples under uniaxial tensile deformation at different exposure times through Marine exposure experiments.We obtained the strain evolution by digital image correlation(DIC).The strain field images are voxelized using 2D-Convolutional Neural Networks(CNN)autoencoders as input data for Long Short-Term Memory(LSTM)neural networks.Then,the output data of LSTM neural networks combined with corrosion features were input into the Back Propagation(BP)neural network to predict the mechanical properties of Al-Li alloys.The main conclusions are as follows:1.The variation law of mechanical properties of2297-T8 in the Marine atmosphere is revealed.With the increase in outdoor exposure test time,the tensile elastic model of 2297-T8 changes slowly,within 10%,and the tensile yield stress changes significantly,with a maximum attenuation of 23.6%.2.The prediction model can predict the strain evolution and mechanical response simultaneously with an error of less than 5%.3.This study shows that a CNN/LSTM system based on machine learning can be built to capture the corrosion characteristics of Marine exposure experiments.The results show that the relationship between corrosion characteristics and mechanical response can be predicted without considering the microstructure evolution of metal materials.展开更多
An obstacle perception system for intelligent vehicle is proposed.The proposed system combines the stereo version technique and the deep learning network model,and is applied to obstacle perception tasks in complex en...An obstacle perception system for intelligent vehicle is proposed.The proposed system combines the stereo version technique and the deep learning network model,and is applied to obstacle perception tasks in complex environment.In this paper,we provide a complete system design project,which includes the hardware parameters,software framework,algorithm principle,and optimization method.In addition,special experiments are designed to demonstrate that the performance of the proposed system meets the requirements of actual application.The experiment results show that the proposed system is valid to both standard obstacles and non-standard obstacles,and suitable for different weather and lighting conditions in complex environment.It announces that the proposed system is flexible and robust to the intelligent vehicle.展开更多
针对多目标狼群算法存在的搜索不充分、收敛性不足和多样性欠缺的问题,以及缺少对约束进行处理的问题,提出环境选择的双种群约束多目标狼群算法(multi-objective wolf pack algorithm for dual population constraints with environment...针对多目标狼群算法存在的搜索不充分、收敛性不足和多样性欠缺的问题,以及缺少对约束进行处理的问题,提出环境选择的双种群约束多目标狼群算法(multi-objective wolf pack algorithm for dual population constraints with environment selection,DCMOWPA-ES)。引入双种群约束处理方法给种群设置不同的搜索偏好,主种群运用可行性准则优先保留可行解,次种群通过ε约束探索不可行区域并将搜索结果传递给主种群,让算法能较好应对复杂的不可行区域,保障算法的可行性;提出维度选择的随机游走策略,使人工狼可自主选择游走方向,提高种群的全局搜索能力;设计精英学习的步长调整机制,人工狼通过向头狼学习的方式提升种群的局部搜索能力,确保算法的收敛性;采用环境选择的狼群更新策略,根据人工狼被支配的情况和所处位置的密度信息对其赋值,选择被支配数少且密度信息小的人工狼作为优秀个体,改善算法的多样性。为验证算法性能,将DCMOWPA-ES与六种新兴约束多目标优化算法在两组约束多目标测试集和汽车侧面碰撞设计问题上进行对比实验。实验结果表明,DCMOWPA-ES算法具备较好的可行性、收敛性和多样性。展开更多
针对暗环境动态特征轮廓模糊、盲区遮挡情况,高效准确地检测跟踪动态目标特征,对灾害救援、搜寻跟踪具有实际意义。为实现暗环境下模糊轮廓特征的有效检测跟踪,提出一种时空关联机制的红外目标实时检测深度学习网络(Spatial Local Dynam...针对暗环境动态特征轮廓模糊、盲区遮挡情况,高效准确地检测跟踪动态目标特征,对灾害救援、搜寻跟踪具有实际意义。为实现暗环境下模糊轮廓特征的有效检测跟踪,提出一种时空关联机制的红外目标实时检测深度学习网络(Spatial Local Dynamic You Only Look Once Version 8,SLD-YOLOv8),设计非局部自适应Non-local模块和空间通道卷积关联模块,对原YOLOv8网络的瓶颈层Bottleneck CSP进行优化。为有效提取深层空间多尺度表征信息,增加用于小目标检测的160×160检测层和动态检测头,较好地提升暗环境中目标跟踪的边界回归性能,并实时有效地推理出目标特征的相对深度位置信息。实验结果表明,改进后的红外目标检测算法对暗环境下的动态特征检测具有较好的鲁棒性和准确性,其平均精度评估指标mAP_0.5和mAP_0.5:0.95比原模型提高了5.6%和4.5%,证明了新算法对暗环境目标跟踪的有效性。展开更多
基金The National Natural Science Foundation of China (32371993)The Natural Science Research Key Project of Anhui Provincial University(2022AH040125&2023AH040135)The Key Research and Development Plan of Anhui Province (202204c06020022&2023n06020057)。
文摘This study aimed to address the challenge of accurately and reliably detecting tomatoes in dense planting environments,a critical prerequisite for the automation implementation of robotic harvesting.However,the heavy reliance on extensive manually annotated datasets for training deep learning models still poses significant limitations to their application in real-world agricultural production environments.To overcome these limitations,we employed domain adaptive learning approach combined with the YOLOv5 model to develop a novel tomato detection model called as TDA-YOLO(tomato detection domain adaptation).We designated the normal illumination scenes in dense planting environments as the source domain and utilized various other illumination scenes as the target domain.To construct bridge mechanism between source and target domains,neural preset for color style transfer is introduced to generate a pseudo-dataset,which served to deal with domain discrepancy.Furthermore,this study combines the semi-supervised learning method to enable the model to extract domain-invariant features more fully,and uses knowledge distillation to improve the model's ability to adapt to the target domain.Additionally,for purpose of promoting inference speed and low computational demand,the lightweight FasterNet network was integrated into the YOLOv5's C3 module,creating a modified C3_Faster module.The experimental results demonstrated that the proposed TDA-YOLO model significantly outperformed original YOLOv5s model,achieving a mAP(mean average precision)of 96.80%for tomato detection across diverse scenarios in dense planting environments,increasing by 7.19 percentage points;Compared with the latest YOLOv8 and YOLOv9,it is also 2.17 and 1.19 percentage points higher,respectively.The model's average detection time per image was an impressive 15 milliseconds,with a FLOPs(floating point operations per second)count of 13.8 G.After acceleration processing,the detection accuracy of the TDA-YOLO model on the Jetson Xavier NX development board is 90.95%,the mAP value is 91.35%,and the detection time of each image is 21 ms,which can still meet the requirements of real-time detection of tomatoes in dense planting environment.The experimental results show that the proposed TDA-YOLO model can accurately and quickly detect tomatoes in dense planting environment,and at the same time avoid the use of a large number of annotated data,which provides technical support for the development of automatic harvesting systems for tomatoes and other fruits.
基金the Natural Science Foundation of Shaan’xi Province (2005F51).
文摘Because most ensemble learning algorithms use the centralized model, and the training instances must be centralized on a single station, it is difficult to centralize the training data on a station. A distributed ensemble learning algorithm is proposed which has two kinds of weight genes of instances that denote the global distribution and the local distribution. Instead of the repeated sampling method in the standard ensemble learning, non-balance sampling from each station is used to train the base classifier set of each station. The concept of the effective nearby region for local integration classifier is proposed, and is used for the dynamic integration method of multiple classifiers in distributed environment. The experiments show that the ensemble learning algorithm in distributed environment proposed could reduce the time of training the base classifiers effectively, and ensure the classify performance is as same as the centralized learning method.
文摘From the viewpoint of psycholinguistics, this paper concerns how to create an optimal language learning environment in language learning, to stimulate students enthusiasm to participate in classroom activities and to make language learning easier and more pleasant.
基金supported by the Southwest Institute of Technology and Engineering cooperation fund(Grant No.HDHDW5902020104)。
文摘The ocean is one of the essential fields of national defense in the future,and more and more attention is paid to the lightweight research of Marine equipment and materials.This study it is to develop a Machine learning(ML)-based prediction method to study the evolution of the mechanical properties of Al-Li alloys in the marine environment.We obtained the mechanical properties of Al-Li alloy samples under uniaxial tensile deformation at different exposure times through Marine exposure experiments.We obtained the strain evolution by digital image correlation(DIC).The strain field images are voxelized using 2D-Convolutional Neural Networks(CNN)autoencoders as input data for Long Short-Term Memory(LSTM)neural networks.Then,the output data of LSTM neural networks combined with corrosion features were input into the Back Propagation(BP)neural network to predict the mechanical properties of Al-Li alloys.The main conclusions are as follows:1.The variation law of mechanical properties of2297-T8 in the Marine atmosphere is revealed.With the increase in outdoor exposure test time,the tensile elastic model of 2297-T8 changes slowly,within 10%,and the tensile yield stress changes significantly,with a maximum attenuation of 23.6%.2.The prediction model can predict the strain evolution and mechanical response simultaneously with an error of less than 5%.3.This study shows that a CNN/LSTM system based on machine learning can be built to capture the corrosion characteristics of Marine exposure experiments.The results show that the relationship between corrosion characteristics and mechanical response can be predicted without considering the microstructure evolution of metal materials.
基金supported by the National Natural Science Foundation of China(61673381)the National Key R&D Program of China(2018AAA0103103)the Science and Technology Development Fund(0024/2018/A1)。
文摘An obstacle perception system for intelligent vehicle is proposed.The proposed system combines the stereo version technique and the deep learning network model,and is applied to obstacle perception tasks in complex environment.In this paper,we provide a complete system design project,which includes the hardware parameters,software framework,algorithm principle,and optimization method.In addition,special experiments are designed to demonstrate that the performance of the proposed system meets the requirements of actual application.The experiment results show that the proposed system is valid to both standard obstacles and non-standard obstacles,and suitable for different weather and lighting conditions in complex environment.It announces that the proposed system is flexible and robust to the intelligent vehicle.
文摘针对多目标狼群算法存在的搜索不充分、收敛性不足和多样性欠缺的问题,以及缺少对约束进行处理的问题,提出环境选择的双种群约束多目标狼群算法(multi-objective wolf pack algorithm for dual population constraints with environment selection,DCMOWPA-ES)。引入双种群约束处理方法给种群设置不同的搜索偏好,主种群运用可行性准则优先保留可行解,次种群通过ε约束探索不可行区域并将搜索结果传递给主种群,让算法能较好应对复杂的不可行区域,保障算法的可行性;提出维度选择的随机游走策略,使人工狼可自主选择游走方向,提高种群的全局搜索能力;设计精英学习的步长调整机制,人工狼通过向头狼学习的方式提升种群的局部搜索能力,确保算法的收敛性;采用环境选择的狼群更新策略,根据人工狼被支配的情况和所处位置的密度信息对其赋值,选择被支配数少且密度信息小的人工狼作为优秀个体,改善算法的多样性。为验证算法性能,将DCMOWPA-ES与六种新兴约束多目标优化算法在两组约束多目标测试集和汽车侧面碰撞设计问题上进行对比实验。实验结果表明,DCMOWPA-ES算法具备较好的可行性、收敛性和多样性。
文摘针对暗环境动态特征轮廓模糊、盲区遮挡情况,高效准确地检测跟踪动态目标特征,对灾害救援、搜寻跟踪具有实际意义。为实现暗环境下模糊轮廓特征的有效检测跟踪,提出一种时空关联机制的红外目标实时检测深度学习网络(Spatial Local Dynamic You Only Look Once Version 8,SLD-YOLOv8),设计非局部自适应Non-local模块和空间通道卷积关联模块,对原YOLOv8网络的瓶颈层Bottleneck CSP进行优化。为有效提取深层空间多尺度表征信息,增加用于小目标检测的160×160检测层和动态检测头,较好地提升暗环境中目标跟踪的边界回归性能,并实时有效地推理出目标特征的相对深度位置信息。实验结果表明,改进后的红外目标检测算法对暗环境下的动态特征检测具有较好的鲁棒性和准确性,其平均精度评估指标mAP_0.5和mAP_0.5:0.95比原模型提高了5.6%和4.5%,证明了新算法对暗环境目标跟踪的有效性。
