In mobile edge networks, federated learning (FL) has garnered substantial attention as a distributed machine learning framework with significant advantages for protecting user privacy. Due to the limited resources of ...
详细信息
Efficient energy management is a cornerstone of advancing cognitive cities,where AI,IoT,and cloud computing seamlessly integrate to meet escalating global energy *** this context,the ability to forecast electricity co...
详细信息
Efficient energy management is a cornerstone of advancing cognitive cities,where AI,IoT,and cloud computing seamlessly integrate to meet escalating global energy *** this context,the ability to forecast electricity consumption with precision is vital,particularly in residential settings where usage patterns are highly variable and *** study presents an innovative approach to energy consumption forecasting using a bidirectional Long short-Term Memory(LsTM)*** a dataset containing over twomillionmultivariate,time-series observations collected froma single household over nearly four years,ourmodel addresses the limitations of traditional time-series forecasting methods,which often struggle with temporal dependencies and non-linear *** bidirectional LsTM architecture processes data in both forward and backward directions,capturing past and future contexts at each time step,whereas existing unidirectional LsTMs consider only a single temporal *** design,combined with dropout regularization,leads to a 20.6%reduction in RMsE and an 18.8%improvement in MAE over conventional unidirectional LsTMs,demonstrating a substantial enhancement in prediction accuracy and *** to existing models—including sVM,Random Forest,MLP,ANN,and CNN—the proposed model achieves the lowest MAE of 0.0831 and RMsE of 0.2213 during testing,significantly outperforming these *** results highlight the model’ssuperior ability to navigate the complexities of energy usage patterns,reinforcing its potential application in AI-driven IoT and cloud-enabled energy management systems for cognitive *** integrating advanced machine learning techniqueswith IoT and cloud infrastructure,thisresearch contributes to the development of intelligent,sustainable urban environments.
Multi-agent Reinforcement learning(MARL)has become one of the best methods in Adaptive Traffic signal Control(ATsC).Traffic flow is a very regular traffic volume,which is highly critical to signal control ***,dynamic ...
详细信息
Multi-agent Reinforcement learning(MARL)has become one of the best methods in Adaptive Traffic signal Control(ATsC).Traffic flow is a very regular traffic volume,which is highly critical to signal control ***,dynamic control policies will directly affect traffic flow formation,and it is impossible to provide observation through the original traffic flow *** paper proposes a method for estimating traffic flow according to the time window in Reinforcement learning(RL)***,it is verified on both the regular road network and the real road *** method further reduces the intersection delay and queue length compared with the original method.
Ensuring the precise anticipation of a driver’s attention is crucial for upholding safety in diverse human-centric transportation scenarios. This capability proves invaluable for discerning and evaluating accident ri...
详细信息
This paper introduces an advanced and efficient method for distributed drone-based fruit recognition and localization, tailored to satisfy the precision and security requirements of autonomous agricultural operations....
详细信息
This paper introduces an advanced and efficient method for distributed drone-based fruit recognition and localization, tailored to satisfy the precision and security requirements of autonomous agricultural operations. Our method incorporates depth information to ensure precise localization and utilizes a streamlined detection network centered on the RepVGG module. This module replaces the traditional C2f module, enhancing detection performance while maintaining speed. To bolster the detection of small, distant fruits in complex settings, we integrate selective Kernel Attention (sKAttention) and a specialized small-target detection layer. This adaptation allows the system to manage difficult conditions, such as variable lighting and obstructive foliage. To reinforce security, the tasks of recognition and localization are distributed among multiple drones, enhancing resilience against tampering and data manipulation. This distribution also optimizes resource allocation through collaborative processing. The model remains lightweight and is optimized for rapid and accurate detection, which is essential for real-time applications. Our proposed system, validated with a D435 depth camera, achieves a mean Average Precision (mAP) of 0.943 and a frame rate of 169 FPs, which represents a significant improvement over the baseline by 0.039 percentage points and 25 FPs, respectively. Additionally, the average localization error is reduced to 0.82 cm, highlighting the model’s high precision. These enhancements render our system highly effective for secure, autonomous fruit-picking operations, effectively addressing significant performance and cybersecurity challenges in agriculture. This approach establishes a foundation for reliable, efficient, and secure distributed fruit-picking applications, facilitating the advancement of autonomoussystems in contemporary agricultural practices.
Personalized federated learning(PFL) aims to train customized models for individual clients in a decentralized setting, with the account of non-independent and identically distributed data across clients. However, mos...
详细信息
Personalized federated learning(PFL) aims to train customized models for individual clients in a decentralized setting, with the account of non-independent and identically distributed data across clients. However, most PFL methods adopt uniform classification layers for diverse clients and give rise to error-prone predictions, due to the task heterogeneity notably prominent in decentralized graph data scenarios. Although some PFL solutionssetup client-specific classification layers for each client and optimize them only locally, they are corrupted with limited local training data. We propose an innovative solution called federated parameter decoupling and node augmentation(Fed PANo) to address these problems and to achieve personalized federated few-shot node classification, which is a prevalent and challenging but unexplored topic. specifically, Fed PANo first separates the local model into the GNN and classifier to handle unique client-specific task variations. The GNN is trained through federated learning to capture shared knowledge of graph nodes across clients, while the classifier is custom-designed and trained individually for each client. Additionally, a generic classifier shared among clients is adopted to encourage the GNN's grasp of shared information. Then Fed PANo further proposes the node generator along with its local and collaborative training strategies to deal with the node scarcity of clients. Extensive experimental results on benchmark datasets confirm that Fed PANo outperforms eight competitive baselines across different settings.
Thisresearch focuses on utilizing data-driven machine learning techniques to study the impact of air pollution on the health of residents in industrial regions. The objective is to develop an efficient machine learni...
详细信息
Federated learning is an emerging privacy-preserving distributed learning paradigm,in which many clients collaboratively train a shared global model under the orchestration of a remote *** current works on federated l...
详细信息
Federated learning is an emerging privacy-preserving distributed learning paradigm,in which many clients collaboratively train a shared global model under the orchestration of a remote *** current works on federated learning have focused on fully supervised learningsettings,assuming that all the data are annotated with ground-truth ***,this work considers a more realistic and challenging setting,Federated semi-supervised learning(FssL),where clients have a large amount of unlabeled data and only the server hosts a small number of labeled *** to reasonably utilize the server-side labeled data and the client-side unlabeled data is the core challenge in this *** this paper,we propose a new FssL algorithm for image classification based on consistency regularization and ensemble knowledge distillation,called *** algorithm uses the global model as the teacher in consistency regularization methods to enhance both the accuracy and stability of client-side unsupervised learning on unlabeled ***,we introduce an additional ensemble knowledge distillation loss to mitigate model overfitting during server-side retraining on labeled *** experiments on several image classification datasetsshow that our EKDFssL outperforms current baseline methods.
As microplastic (MP) particles continue to spread globally, their pervasive presence is increasingly problematic. Analyzing MPs in matrices as varied assoil, river water, and biosolid fertilizers is critical, as thes...
详细信息
As microplastic (MP) particles continue to spread globally, their pervasive presence is increasingly problematic. Analyzing MPs in matrices as varied assoil, river water, and biosolid fertilizers is critical, as these matrices directly impact the food sources of plants, animals, and humans. Current analytical methods for quantifying and identifying MPs are limited due to labor-intensive extraction processes and the time and effort required for counting and analysis. Recently, Machine learning (ML) has been introduced to the analysis of MPs in complex matrices, significantly reducing the need for extensive extraction and increasing analysisspeeds. This work aims to illuminate various ML techniques for new researchers entering this field. It highlights numerous examples in the application of these models, with a particular focus on spectroscopic techniquessuch as infrared and Raman spectroscopy;tools which are used to quantify and identify MPs in complex matrices. By demonstrating the effectiveness of these computer-based tools alongside the hands-on techniques currently used in the field, we are confident that these ML methodologies will soon become integral to all aspects of microplastic analysis in the environmental sciences.
The process of error detection, explanation, and correction is essential in project making. such structured error-basedlearning is thought to occur via active exploration of metacognitive processes. To understand how...
详细信息
暂无评论