The power grid operation process is complex,and many operation process data involve national security,business secrets,and user ***,labeled datasets may exist in many different operation platforms,but they cannot be d...
详细信息
The power grid operation process is complex,and many operation process data involve national security,business secrets,and user ***,labeled datasets may exist in many different operation platforms,but they cannot be directly shared since power grid data is highly *** to use these multi-source heterogeneous data as much as possible to build a power grid knowledge map under the premise of protecting privacy security has become an urgent problem in developing smart ***,this paper proposes federated learning named entity recognition method for the power grid field,aiming to solve the problem of building a named entity recognition model covering the entire power grid process training by data with different security *** decompose the named entity recognition(NER)model FLAT(Chinese NER Using Flat-Lattice Transformer)in each platform into a global part and a local *** local part is used to capture the characteristics of the local data in each platform and is updated using locally labeled *** global part is learned across different operation platforms to capture the shared NER *** local gradients fromdifferent platforms are aggregated to update the global model,which is further delivered to each platform to update their global *** on two publicly available Chinese datasets and one power grid dataset validate the effectiveness of our method.
Natural language processing (NLP) is one of the most popular proliferating research fields nowadays in artificial intelligence and machine learning. NLP deals with numerous applications such as Sentiment Analysis, Spe...
详细信息
Accidents on railroad tracks continue even with human inspections, which are often inaccurate and can lead to serious incidents. While artificial intelligence has found use in the railway sector, computer vision-based...
详细信息
This research introduces a novel approach to multi-class classification, harnessing hierarchical architectures to enhance accuracy and interpretability. Specialized models are designed at each hierarchy level, capturi...
详细信息
Natural disasters present major obstacles to global disaster management initiatives and the potential for integrating Artificial Intelligence (AI) techniques into disaster management decision-support systems in order ...
详细信息
Several attacks pose serious dangers to vehicular networks (VN), crucial to creating smart transportation systems (ITS). Due to ITS, VN has become more important since it allows for smooth communication between infras...
详细信息
Cancer gene expression data analysis using microarray technology is a critical domain in understanding the molecular intricacies of malignancy. With an emphasis on the incorporation of data augmentation techniques, th...
详细信息
Recommendation engines are extremely important in the constantly changing world of online business. This paper describes a deep learning-based product recommendation system that skillfully combines text and image cate...
详细信息
In dense crowd scenes, the scale of human heads varies greatly, and current visual transformer models lack learning of different scales, resulting in the model being unable to perceive the target scale changes of huma...
详细信息
In the fast-changing environment of intelligent transportation systems, vehicular fog computing (VFC) is emerging as a critical technology for real-time data processing at the network's edge. This study describes ...
详细信息
暂无评论