[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-base...[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.展开更多
Mill vibration is a common problem in rolling production,which directly affects the thickness accuracy of the strip and may even lead to strip fracture accidents in serious cases.The existing vibration prediction mode...Mill vibration is a common problem in rolling production,which directly affects the thickness accuracy of the strip and may even lead to strip fracture accidents in serious cases.The existing vibration prediction models do not consider the features contained in the data,resulting in limited improvement of model accuracy.To address these challenges,this paper proposes a multi-dimensional multi-modal cold rolling vibration time series prediction model(MDMMVPM)based on the deep fusion of multi-level networks.In the model,the long-term and short-term modal features of multi-dimensional data are considered,and the appropriate prediction algorithms are selected for different data features.Based on the established prediction model,the effects of tension and rolling force on mill vibration are analyzed.Taking the 5th stand of a cold mill in a steel mill as the research object,the innovative model is applied to predict the mill vibration for the first time.The experimental results show that the correlation coefficient(R^(2))of the model proposed in this paper is 92.5%,and the root-mean-square error(RMSE)is 0.0011,which significantly improves the modeling accuracy compared with the existing models.The proposed model is also suitable for the hot rolling process,which provides a new method for the prediction of strip rolling vibration.展开更多
Intelligent personal assistants play a pivotal role in in-vehicle systems,significantly enhancing life efficiency,driving safety,and decision-making support.In this study,the multi-modal design elements of intelligent...Intelligent personal assistants play a pivotal role in in-vehicle systems,significantly enhancing life efficiency,driving safety,and decision-making support.In this study,the multi-modal design elements of intelligent personal assistants within the context of visual,auditory,and somatosensory interactions with drivers were discussed.Their impact on the driver’s psychological state through various modes such as visual imagery,voice interaction,and gesture interaction were explored.The study also introduced innovative designs for in-vehicle intelligent personal assistants,incorporating design principles such as driver-centricity,prioritizing passenger safety,and utilizing timely feedback as a criterion.Additionally,the study employed design methods like driver behavior research and driving situation analysis to enhance the emotional connection between drivers and their vehicles,ultimately improving driver satisfaction and trust.展开更多
A novel immune genetic algorithm with the elitist selection and elitist crossover was proposed, which is called the immune genetic algorithm with the elitism （IGAE）. In IGAE, the new methods for computing antibody s...A novel immune genetic algorithm with the elitist selection and elitist crossover was proposed, which is called the immune genetic algorithm with the elitism （IGAE）. In IGAE, the new methods for computing antibody similarity, expected reproduction probability, and clonal selection probability were given. IGAE has three features. The first is that the similarities of two antibodies in structure and quality are all defined in the form of percentage, which helps to describe the similarity of two antibodies more accurately and to reduce the computational burden effectively. The second is that with the elitist selection and elitist crossover strategy IGAE is able to find the globally optimal solution of a given problem. The third is that the formula of expected reproduction probability of antibody can be adjusted through a parameter r, which helps to balance the population diversity and the convergence speed of IGAE so that IGAE can find the globally optimal solution of a given problem more rapidly. Two different complex multi-modal functions were selected to test the validity of IGAE. The experimental results show that IGAE can find the globally maximum/minimum values of the two functions rapidly. The experimental results also confirm that IGAE is of better performance in convergence speed, solution variation behavior, and computational efficiency compared with the canonical genetic algorithm with the elitism and the immune genetic algorithm with the information entropy and elitism.展开更多
Laser cleaning is a highly nonlinear physical process for solving poor single-modal(e.g., acoustic or vision)detection performance and low inter-information utilization. In this study, a multi-modal feature fusion net...Laser cleaning is a highly nonlinear physical process for solving poor single-modal(e.g., acoustic or vision)detection performance and low inter-information utilization. In this study, a multi-modal feature fusion network model was constructed based on a laser paint removal experiment. The alignment of heterogeneous data under different modals was solved by combining the piecewise aggregate approximation and gramian angular field. Moreover, the attention mechanism was introduced to optimize the dual-path network and dense connection network, enabling the sampling characteristics to be extracted and integrated. Consequently, the multi-modal discriminant detection of laser paint removal was realized. According to the experimental results, the verification accuracy of the constructed model on the experimental dataset was 99.17%, which is 5.77% higher than the optimal single-modal detection results of the laser paint removal. The feature extraction network was optimized by the attention mechanism, and the model accuracy was increased by 3.3%. Results verify the improved classification performance of the constructed multi-modal feature fusion model in detecting laser paint removal, the effective integration of acoustic data and visual image data, and the accurate detection of laser paint removal.展开更多
A new coarse-to-fine strategy was proposed for nonrigid registration of computed tomography(CT) and magnetic resonance(MR) images of a liver.This hierarchical framework consisted of an affine transformation and a B-sp...A new coarse-to-fine strategy was proposed for nonrigid registration of computed tomography(CT) and magnetic resonance(MR) images of a liver.This hierarchical framework consisted of an affine transformation and a B-splines free-form deformation(FFD).The affine transformation performed a rough registration targeting the mismatch between the CT and MR images.The B-splines FFD transformation performed a finer registration by correcting local motion deformation.In the registration algorithm,the normalized mutual information(NMI) was used as similarity measure,and the limited memory Broyden-Fletcher- Goldfarb-Shannon(L-BFGS) optimization method was applied for optimization process.The algorithm was applied to the fully automated registration of liver CT and MR images in three subjects.The results demonstrate that the proposed method not only significantly improves the registration accuracy but also reduces the running time,which is effective and efficient for nonrigid registration.展开更多
Deep multi-modal learning,a rapidly growing field with a wide range of practical applications,aims to effectively utilize and integrate information from multiple sources,known as modalities.Despite its impressive empi...Deep multi-modal learning,a rapidly growing field with a wide range of practical applications,aims to effectively utilize and integrate information from multiple sources,known as modalities.Despite its impressive empirical performance,the theoretical foundations of deep multi-modal learning have yet to be fully explored.In this paper,we will undertake a comprehensive survey of recent developments in multi-modal learning theories,focusing on the fundamental properties that govern this field.Our goal is to provide a thorough collection of current theoretical tools for analyzing multi-modal learning,to clarify their implications for practitioners,and to suggest future directions for the establishment of a solid theoretical foundation for deep multi-modal learning.展开更多
随着社交网络平台的迅速发展,网络欺凌问题日益突出,文本与图片相结合的多样化网络表达形式提高了网络欺凌的检测和治理难度.构建了一个包含文本和图片的中文多模态网络欺凌数据集,将BERT(bidirectional encoder representations from t...随着社交网络平台的迅速发展,网络欺凌问题日益突出,文本与图片相结合的多样化网络表达形式提高了网络欺凌的检测和治理难度.构建了一个包含文本和图片的中文多模态网络欺凌数据集,将BERT(bidirectional encoder representations from transformers)模型与ResNet50模型相结合,分别提取文本和图片的单模态特征,并进行决策层融合,对融合后的特征进行检测,实现了对网络欺凌与非网络欺凌2个类别的文本和图片的准确识别.实验结果表明,提出的多模态网络欺凌检测模型能够有效识别出包含文本与图片的具有网络欺凌性质的社交网络帖子或者评论,提高了多模态形式网络欺凌检测的实用性、准确性和效率,为社交网络平台的网络欺凌检测和治理提供了一种新的思路和方法,有助于构建更加健康、文明的网络环境.展开更多
输电线路巡检中采集的螺栓图像有分辨率低、视觉信息不足的特点。针对传统图像分类模型难以从螺栓图像中学习到语义丰富的视觉表征问题,提出了一种基于多模态对比学习的输电线路螺栓缺陷分类方法。首先,为了将文本中螺栓相关的语义信息...输电线路巡检中采集的螺栓图像有分辨率低、视觉信息不足的特点。针对传统图像分类模型难以从螺栓图像中学习到语义丰富的视觉表征问题,提出了一种基于多模态对比学习的输电线路螺栓缺陷分类方法。首先,为了将文本中螺栓相关的语义信息和先验知识以跨模态的方式注入视觉表征,提出了一种结合多模态对比预训练和监督式微调的二阶段训练算法;其次,为了缓解多模态对比预训练中的过拟合问题,提出了标签平滑的信息噪声对比估计损失(info noise contrastive estimation loss with label smoothing,infoNCE-LS),以提高预训练视觉表征的泛化性能;最后,针对上下游任务的不匹配问题,设计了3种基于文本提示的分类头,以改善预训练视觉表征在监督式微调阶段的迁移学习效果。实验结果表明:该文基于Res Net50和ViT构建的两种模型在螺栓缺陷分类数据集上的准确率分别为92.3%和97.4%,相比基线分别提高了2.4%和5.8%。研究实现了从文本到图像的语义信息跨模态补充,为螺栓缺陷识别的研究提供了新的思路。展开更多
命名实体识别任务旨在识别出非结构化文本中所包含的实体并将其分配给预定义的实体类别中.随着互联网和社交媒体的发展,文本信息往往伴随着图像等视觉模态信息出现,传统的命名实体识别方法在多模态信息中表现不佳.近年来,多模态命名实...命名实体识别任务旨在识别出非结构化文本中所包含的实体并将其分配给预定义的实体类别中.随着互联网和社交媒体的发展,文本信息往往伴随着图像等视觉模态信息出现,传统的命名实体识别方法在多模态信息中表现不佳.近年来,多模态命名实体识别任务广受重视.然而,现有的多模态命名实体识别方法中,存在跨模态知识间的细粒度对齐不足问题,文本表征会融合语义不相关的图像信息,进而引入噪声.为了解决这些问题,提出了一种基于细粒度图文对齐的多模态命名实体识别方法(FGITA:A Multi-Modal NER Frame based on Fine-Grained Image-Text Alignment).首先,该方法通过目标检测、语义相似性判断等,确定更为细粒度的文本实体和图像子对象之间的语义相关性;其次,通过双线性注意力机制,计算出图像子对象与实体的相关性权重,并依据权重将子对象信息融入到实体表征中;最后,提出了一种跨模态对比学习方法,依据图像和实体之间的匹配程度,优化实体和图像在嵌入空间中的距离,借此帮助实体表征学习相关的图像信息.在两个公开数据集上的实验表明,FGITA优于5个主流多模态命名实体识别方法,验证了方法的有效性,同时验证了细粒度跨模态对齐在多模态命名实体识别任务中的重要性和优越性.展开更多
文摘[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.
基金Project(2023JH26-10100002)supported by the Liaoning Science and Technology Major Project,ChinaProjects(U21A20117,52074085)supported by the National Natural Science Foundation of China+1 种基金Project(2022JH2/101300008)supported by the Liaoning Applied Basic Research Program Project,ChinaProject(22567612H)supported by the Hebei Provincial Key Laboratory Performance Subsidy Project,China。
文摘Mill vibration is a common problem in rolling production,which directly affects the thickness accuracy of the strip and may even lead to strip fracture accidents in serious cases.The existing vibration prediction models do not consider the features contained in the data,resulting in limited improvement of model accuracy.To address these challenges,this paper proposes a multi-dimensional multi-modal cold rolling vibration time series prediction model(MDMMVPM)based on the deep fusion of multi-level networks.In the model,the long-term and short-term modal features of multi-dimensional data are considered,and the appropriate prediction algorithms are selected for different data features.Based on the established prediction model,the effects of tension and rolling force on mill vibration are analyzed.Taking the 5th stand of a cold mill in a steel mill as the research object,the innovative model is applied to predict the mill vibration for the first time.The experimental results show that the correlation coefficient(R^(2))of the model proposed in this paper is 92.5%,and the root-mean-square error(RMSE)is 0.0011,which significantly improves the modeling accuracy compared with the existing models.The proposed model is also suitable for the hot rolling process,which provides a new method for the prediction of strip rolling vibration.
文摘Intelligent personal assistants play a pivotal role in in-vehicle systems,significantly enhancing life efficiency,driving safety,and decision-making support.In this study,the multi-modal design elements of intelligent personal assistants within the context of visual,auditory,and somatosensory interactions with drivers were discussed.Their impact on the driver’s psychological state through various modes such as visual imagery,voice interaction,and gesture interaction were explored.The study also introduced innovative designs for in-vehicle intelligent personal assistants,incorporating design principles such as driver-centricity,prioritizing passenger safety,and utilizing timely feedback as a criterion.Additionally,the study employed design methods like driver behavior research and driving situation analysis to enhance the emotional connection between drivers and their vehicles,ultimately improving driver satisfaction and trust.
基金Project(50275150) supported by the National Natural Science Foundation of ChinaProjects(20040533035, 20070533131) supported by the National Research Foundation for the Doctoral Program of Higher Education of China
文摘A novel immune genetic algorithm with the elitist selection and elitist crossover was proposed, which is called the immune genetic algorithm with the elitism （IGAE）. In IGAE, the new methods for computing antibody similarity, expected reproduction probability, and clonal selection probability were given. IGAE has three features. The first is that the similarities of two antibodies in structure and quality are all defined in the form of percentage, which helps to describe the similarity of two antibodies more accurately and to reduce the computational burden effectively. The second is that with the elitist selection and elitist crossover strategy IGAE is able to find the globally optimal solution of a given problem. The third is that the formula of expected reproduction probability of antibody can be adjusted through a parameter r, which helps to balance the population diversity and the convergence speed of IGAE so that IGAE can find the globally optimal solution of a given problem more rapidly. Two different complex multi-modal functions were selected to test the validity of IGAE. The experimental results show that IGAE can find the globally maximum/minimum values of the two functions rapidly. The experimental results also confirm that IGAE is of better performance in convergence speed, solution variation behavior, and computational efficiency compared with the canonical genetic algorithm with the elitism and the immune genetic algorithm with the information entropy and elitism.
基金Project(51875491) supported by the National Natural Science Foundation of ChinaProject(2021T3069) supported by the Fujian Science and Technology Plan STS Project,China。
文摘Laser cleaning is a highly nonlinear physical process for solving poor single-modal(e.g., acoustic or vision)detection performance and low inter-information utilization. In this study, a multi-modal feature fusion network model was constructed based on a laser paint removal experiment. The alignment of heterogeneous data under different modals was solved by combining the piecewise aggregate approximation and gramian angular field. Moreover, the attention mechanism was introduced to optimize the dual-path network and dense connection network, enabling the sampling characteristics to be extracted and integrated. Consequently, the multi-modal discriminant detection of laser paint removal was realized. According to the experimental results, the verification accuracy of the constructed model on the experimental dataset was 99.17%, which is 5.77% higher than the optimal single-modal detection results of the laser paint removal. The feature extraction network was optimized by the attention mechanism, and the model accuracy was increased by 3.3%. Results verify the improved classification performance of the constructed multi-modal feature fusion model in detecting laser paint removal, the effective integration of acoustic data and visual image data, and the accurate detection of laser paint removal.
基金Project(61240010)supported by the National Natural Science Foundation of ChinaProject(20070007070)supported by Specialized Research Fund for the Doctoral Program of Higher Education of China
文摘A new coarse-to-fine strategy was proposed for nonrigid registration of computed tomography(CT) and magnetic resonance(MR) images of a liver.This hierarchical framework consisted of an affine transformation and a B-splines free-form deformation(FFD).The affine transformation performed a rough registration targeting the mismatch between the CT and MR images.The B-splines FFD transformation performed a finer registration by correcting local motion deformation.In the registration algorithm,the normalized mutual information(NMI) was used as similarity measure,and the limited memory Broyden-Fletcher- Goldfarb-Shannon(L-BFGS) optimization method was applied for optimization process.The algorithm was applied to the fully automated registration of liver CT and MR images in three subjects.The results demonstrate that the proposed method not only significantly improves the registration accuracy but also reduces the running time,which is effective and efficient for nonrigid registration.
基金Supported by Technology and Innovation Major Project of the Ministry of Science and Technology of China(2020AAA0108400, 2020AAA0108403)Tsinghua Precision Medicine Foundation(10001020109)。
文摘Deep multi-modal learning,a rapidly growing field with a wide range of practical applications,aims to effectively utilize and integrate information from multiple sources,known as modalities.Despite its impressive empirical performance,the theoretical foundations of deep multi-modal learning have yet to be fully explored.In this paper,we will undertake a comprehensive survey of recent developments in multi-modal learning theories,focusing on the fundamental properties that govern this field.Our goal is to provide a thorough collection of current theoretical tools for analyzing multi-modal learning,to clarify their implications for practitioners,and to suggest future directions for the establishment of a solid theoretical foundation for deep multi-modal learning.
文摘随着社交网络平台的迅速发展,网络欺凌问题日益突出,文本与图片相结合的多样化网络表达形式提高了网络欺凌的检测和治理难度.构建了一个包含文本和图片的中文多模态网络欺凌数据集,将BERT(bidirectional encoder representations from transformers)模型与ResNet50模型相结合,分别提取文本和图片的单模态特征,并进行决策层融合,对融合后的特征进行检测,实现了对网络欺凌与非网络欺凌2个类别的文本和图片的准确识别.实验结果表明,提出的多模态网络欺凌检测模型能够有效识别出包含文本与图片的具有网络欺凌性质的社交网络帖子或者评论,提高了多模态形式网络欺凌检测的实用性、准确性和效率,为社交网络平台的网络欺凌检测和治理提供了一种新的思路和方法,有助于构建更加健康、文明的网络环境.
文摘输电线路巡检中采集的螺栓图像有分辨率低、视觉信息不足的特点。针对传统图像分类模型难以从螺栓图像中学习到语义丰富的视觉表征问题,提出了一种基于多模态对比学习的输电线路螺栓缺陷分类方法。首先,为了将文本中螺栓相关的语义信息和先验知识以跨模态的方式注入视觉表征,提出了一种结合多模态对比预训练和监督式微调的二阶段训练算法;其次,为了缓解多模态对比预训练中的过拟合问题,提出了标签平滑的信息噪声对比估计损失(info noise contrastive estimation loss with label smoothing,infoNCE-LS),以提高预训练视觉表征的泛化性能;最后,针对上下游任务的不匹配问题,设计了3种基于文本提示的分类头,以改善预训练视觉表征在监督式微调阶段的迁移学习效果。实验结果表明:该文基于Res Net50和ViT构建的两种模型在螺栓缺陷分类数据集上的准确率分别为92.3%和97.4%,相比基线分别提高了2.4%和5.8%。研究实现了从文本到图像的语义信息跨模态补充,为螺栓缺陷识别的研究提供了新的思路。
文摘命名实体识别任务旨在识别出非结构化文本中所包含的实体并将其分配给预定义的实体类别中.随着互联网和社交媒体的发展,文本信息往往伴随着图像等视觉模态信息出现,传统的命名实体识别方法在多模态信息中表现不佳.近年来,多模态命名实体识别任务广受重视.然而,现有的多模态命名实体识别方法中,存在跨模态知识间的细粒度对齐不足问题,文本表征会融合语义不相关的图像信息,进而引入噪声.为了解决这些问题,提出了一种基于细粒度图文对齐的多模态命名实体识别方法(FGITA:A Multi-Modal NER Frame based on Fine-Grained Image-Text Alignment).首先,该方法通过目标检测、语义相似性判断等,确定更为细粒度的文本实体和图像子对象之间的语义相关性;其次,通过双线性注意力机制,计算出图像子对象与实体的相关性权重,并依据权重将子对象信息融入到实体表征中;最后,提出了一种跨模态对比学习方法,依据图像和实体之间的匹配程度,优化实体和图像在嵌入空间中的距离,借此帮助实体表征学习相关的图像信息.在两个公开数据集上的实验表明,FGITA优于5个主流多模态命名实体识别方法,验证了方法的有效性,同时验证了细粒度跨模态对齐在多模态命名实体识别任务中的重要性和优越性.
