Local Dataset Research Articles

CFL：Data distribution edge clustering algorithm based on deep Federated learning

Federated learning (FL) allows end-devices to train local models on their respective local datasets and collaborate with the server to train a global predictive model, thus achieving the goal of machine learning while protecting the privacy and sensitive data of end-devices. However, simultaneous access to the server by a large number of end devices may result in increased transmission latency and some local models may have malicious behavior, converging in the opposite direction to the global model. As a result, additional communication costs can occur during the federation learning process. Existing research has mainly focused on reducing the number of communication rounds or cleaning dirty local data. In order to decrease the overall amount of local updates, we provide an edge-based model cleaning and device clustering strategy in this study. By computing the cosine similarity between local update parameters and global model parameters over a multi-dimensional space, the approach assesses if local updates are necessary while preventing pointless communications. In addition, end devices are grouped together based on where they are connected to the network and connect to the cloud via mobile edge nodes in clusters, therefore lowering the latency associated with high concurrent server access. Convolutional neural networks and Soft max regression are used, for instance, to perform MNIST handwritten digit recognition, and the effectiveness of the suggested approach to enhancing communication efficiency is confirmed. According to experimental findings, the edge-based model cleaning and device clustering technique decreases the quantity of local updates by 60% and speeds up the model's convergence by 10.3% when compared to the conventional FL approach.

Generative artificial intelligence for distributed learning to enhance smart grid communication

Machine learning models are the backbone of smart grid optimization, but their effectiveness hinges on access to vast amounts of training data. However, smart grids face critical communication bottlenecks due to the ever-increasing volume of data from distributed sensors. This paper introduces a novel approach leveraging Generative Artificial Intelligence (GenAI), specifically a type of pre-trained Foundation Model (FM) architecture suitable for time series data due to its efficiency and privacy-preserving properties. These GenAI models are distributed to agents, or data holders, empowering them to fine-tune the foundation model with their local datasets. By fine-tuning the foundation model, the updated model can produce synthetic data that mirrors real-world grid conditions. The server aggregates fine-tuned model from all agents and then generates synthetic data which considers all data collected in the grid. This synthetic data can be used to train global machine learning models for specific tasks like anomaly detection and energy optimization. Then, the trained task models are distributed to agents in the grid to leverage them. The paper highlights the advantages of GenAI for smart grid communication, including reduced communication burden, enhanced privacy through anonymized data transmission, and improved efficiency and scalability. By enabling a distributed and intelligent communication architecture, GenAI introduces a novel way for a more secure, efficient, and sustainable energy future.

The First Network of Ocean Bottom Seismometers in the Red Sea to Investigate the Zabargad Fracture Zone

In the last decades, the slow-spreading Red Sea rift has been the objective of several geophysical investigations to study the extension of the oceanic crust, the thickness of the sedimentary cover, and the formation of transform faults. However, local seismology datasets are still lacking despite their potential to contribute to the understanding of the tectonic evolution of the Red Sea. The Zabargad Fracture Zone is located in the Northern Red Sea and significantly offsets the rift axis to the East. Thus, it is considered a key tectonic element to understand better the formation of the Red Sea rift. To fill the gap in the dataset availability, we deployed the first passive seismic network in the Red Sea, within the Zabargad Fracture Zone. This network included 12 Lobster OBSs from the DEPAS pool, 2 OBS developed and deployed by Fugro, and 4 portable seismic land stations deployed on islands and onshore on the Saudi Arabian coast. Our data-quality analysis confirms that the head-buoy cable free to strum, as well as other additional elements of the DEPAS OBSs, generate seismic noise at frequencies $>$ 10 Hz. However, the Fugro OBSs show high-frequency disturbances even if they lack vibrating elements. Comparison between land and OBS stations reveals that noise between 1 and 10 Hz is due to ocean-generated seismic noise, and not due to resonance of the OBS elements. We also found that waveforms of teleseismic earthquakes recorded by the Fugro OBSs, islands, and onshore stations have comparable signal-to-noise ratios. Instead, differences in signal-to-noise ratio for local earthquakes are affected more by site and path effects than instrument settings.

Evidence of a Shallow Magma Reservoir Beneath Askja Caldera, Iceland, From Body Wave Tomography

AbstractIn August 2021, Askja caldera switched to reinflation following ∼40 years of continuous deflation that was first measured some 20 years after its last eruption in 1961. Various lines of evidence, including from geodetic modeling, suggest that both the deflation and reinflation events are related to a shallow magma body. To better understand the subsurface plumbing system, we derive P‐wave velocity (Vp), S‐wave velocity (Vs), and Vp/Vs models of the mid‐upper crust by leveraging a new local earthquake traveltime data set. A cylindrical low‐velocity zone, ∼3 km wide and extending to ∼8 km below sea level (bsl), was imaged beneath the caldera. Within it, two distinct lower velocity and higher Vp/Vs anomalies are illuminated, one centered at ∼0.5 km and the other at ∼6 km bsl. The shallower anomaly lies directly beneath the zone of uplift and is likely associated with the current reinflation event.

Scenario-based Adaptations of Differential Privacy: A Technical Survey

Differential privacy has been a de facto privacy standard in defining privacy and handling privacy preservation. It has had great success in scenarios of local data privacy and statistical dataset privacy. As a primitive definition, standard differential privacy has been adapted to a wide range of practical scenarios. In this work, we summarize differential privacy adaptations in specific scenarios and analyze the correlations between data characteristics and differential privacy design. We mainly present them in two lines including differential privacy adaptations in local data privacy and differential privacy adaptations in statistical dataset privacy. With a focus on differential privacy design, this survey targets providing guiding rules in differential privacy design for scenarios, together with identifying potential opportunities to adaptively apply differential privacy in more emerging technologies and further improve differential privacy itself with the assistance of cryptographic primitives.

Research on soft sensor modeling method for complex chemical processes based on local semi-supervised selective ensemble learning

To address the adverse effects of nonlinearity and dynamic time-varying in complex chemical processes on the accuracy of the soft sensor model, a local-semi-supervised ensemble learning for soft sensor modeling (local semi-supervised-selective ensemble learning-long short term memory, LS-SEL-LSTM) method is proposed in this article. Firstly, a hierarchical clustering method incorporating spatiotemporal criteria is proposed to reduce the influence of nonlinearity in global model prediction accuracy. The method considers the dynamic time-varying characteristics of temporal data and generates multiple local datasets. Then, to address the issue of multi-rate between auxiliary variables and dominant variables, a semi-supervised weight fusion mechanism based on temporal correlation is proposed, which effectively utilizes auxiliary variables to reconstruct local semi-supervised datasets and establishes local soft sensing models using LSTM. Concurrently, the parameters of the established model were optimized using the flower pollination algorithm. Subsequently, a selective ensemble learning method based on sub-model prediction accuracy and an adaptive combination weight calculation method for sub-models were proposed to improve the prediction accuracy. Finally, the effectiveness of the proposed method was verified through the actual dataset of the sulfur recovery process. The results indicate that LS-SEL-LSTM performs well in handling complex chemical processes with nonlinear and dynamic time-varying characteristics.

Measles Vaccine Coverage and Disease Outbreaks: A Systematic Review of the Early Impact of COVID-19 in Low and Lower-Middle Income Countries.

Objectives: We aimed to evaluate changes to measles-containing vaccine (MCV) provision and subsequent measles disease cases in low- and lower-middle income countries (LICs, LMICs) in relation to the COVID-19 pandemic. Methods: A systematic search was conducted of MEDLINE, OVID EMBASE and PubMed records. Primary quantitative and qualitative research studies published from January 2020 were included if they reported on COVID-19 impact on MCV provision and/or measles outbreak rates within LICs and LMICs. Results: 45 studies were included. The change in MCV1 vaccination coverage in national and international regions ranged -13% to +44.4% from pre-COVID time periods. In local regions, the median MCV1 and overall EPI rate changed by -23.3% and -28.5% respectively. Median MCV2 rate was disproportionally impacted in local areas during COVID-interruption time-periods (-48.2%) with ongoing disruption in early-recovery time-periods (-17.7%). 8.9% of studies reported on vaccination status of confirmed measles cases; from these, 71%-91% had received no MCV dose. Conclusion: MCV vaccination coverage experienced ongoing disruption during the recovery periods after initial COVID-19 disruption. Vaccination in local area datasets notably experienced longer-term disruption compared to nationally reported figures.

REMOTE SENSING AND GOOGLE EARTH ENGINE FOR RAPID FLOOD MAPPING AND DAMAGE ASSESSMENT: A CASE OF TYPHOON GONI (ROLLY) AND VAMCO (ULYSSES)

Abstract. Flooding is a devastating natural disaster with global repercussions, affecting human life, crop production, and infrastructure. The increasing frequency and unpredictability of flood events, driven by climate change, highlight the urgent need for rapid and accurate flood mapping and damage assessment. This study explores the use of Google Earth Engine, a web-based platform that utilizes satellite imagery and geospatial data, for flood mapping and damage assessment. By incorporating localized datasets, such as region-specific land cover maps and population density information, the developed workflow provides a robust tool for assessing flood extent, identifying high-risk areas, and estimating the impact on cropland and urban centers. Key findings showed that Cagayan province presented the highest potential flood area, covering approximately 55,063 hectares. This province also had the largest population at risk, with around 39,440 individuals potentially exposed to the effects of flooding. Moreover, the cropland in Cagayan province experienced the most substantial impact, with around 91.26% being affected due to the swelling of the Cagayan River. Camarines Sur experienced severe devastation in urban areas, with about 269 hectares affected by flooding from the Bicol River. This study's findings contribute to a comprehensive understanding of flood impacts beyond the extent of flooding, facilitating informed decision-making, emergency response planning, and targeted interventions to mitigate the effects of floods on communities, agriculture, and urban areas. The approach presented here can be applied in other regions, supporting improved flood management and mitigation strategies for national.

A novel hierarchical framework for plant leaf disease detection using residual vision transformer

Early detection of plant leaf diseases accurately and promptly is very crucial for safeguarding agricultural crop productivity and ensuring food security. During their life cycle, plant leaves get diseased because of multiple factors like bacteria, fungi, weather conditions, etc. In this work, the authors propose a model that aids in the early detection of leaf diseases using a novel hierarchical residual vision transformer using improved Vision Transformer and ResNet9 models. The proposed model can extract more meaningful and discriminating details by reducing the number of trainable parameters with a smaller number of computations. The proposed method is evaluated on the Local Crop dataset, Plant Village dataset, and Extended Plant Village Dataset with 13, 38, and 51 different leaf disease classes. The proposed model is trained using the best trail parameters of Improved Vision Transformer and classified the features using ResNet 9. Performance evaluation is carried out on a wide aspects over the aforementioned datasets and results revealed that the proposed model outperforms other models such as InceptionV3, MobileNetV2, and ResNet50.

Rice Counting and Localization in Unmanned Aerial Vehicle Imagery Using Enhanced Feature Fusion

In rice cultivation and breeding, obtaining accurate information on the quantity and spatial distribution of rice plants is crucial. However, traditional field sampling methods can only provide rough estimates of the plant count and fail to capture precise plant locations. To address these problems, this paper proposes P2PNet-EFF for the counting and localization of rice plants. Firstly, through the introduction of the enhanced feature fusion (EFF), the model improves its ability to integrate deep semantic information while preserving shallow spatial details. This allows the model to holistically analyze the morphology of plants rather than focusing solely on their central points, substantially reducing errors caused by leaf overlap. Secondly, by integrating efficient multi-scale attention (EMA) into the backbone, the model enhances its feature extraction capabilities and suppresses interference from similar backgrounds. Finally, to evaluate the effectiveness of the P2PNet-EFF method, we introduce the URCAL dataset for rice counting and localization, gathered using UAV. This dataset consists of 365 high-resolution images and 173,352 point annotations. Experimental results on the URCAL demonstrate that the proposed method achieves a 34.87% reduction in MAE and a 28.19% reduction in RMSE compared to the original P2PNet while increasing R2 by 3.03%. Furthermore, we conducted extensive experiments on three frequently used plant counting datasets. The results demonstrate the excellent performance of the proposed method.

Industrial federated learning algorithm (P-PFedSGD) for tool wear estimation

In recent years, machine learning has been challenged by the growing concerns regarding data privacy. This has led to the emergence of federated learning, which aims to train a model across distributed clients without sharing their data, thereby resolving the data privacy issues. However, this scheme may not generalize well to the heterogeneous data of distributed clients, particularly in industrial applications. This has motivated the development of personalized approaches for preserving privacy. Therefore, in this study, we introduced an index called gradient divergence to verify heterogeneity based on federated learning, which was adopted to adjust the aggregation weight. A personalized federated learning with privacy preserving algorithm called personalized federated stochastic gradient descent (P-PFedSGD) was developed to improve the performance of federated learning on local datasets while maintaining the performance on other client datasets. P-PFedSGD allows clients to transmit the local gradient instead of the local model. This approach utilizes the advantages of both personalized and federated learning, while preserving data privacy. The developed P-PFedSGD algorithm was applied to tool-wear estimation to demonstrate its performance and effectiveness. The results showed that the developed approach has more functionality than other algorithms to overcome the challenges of federated learning, such as communication cost reduction and computation reduction for clients.

Fully automated explainable abdominal CT contrast media phase classification using organ segmentation and machine learning.

Contrast-enhanced computed tomography (CECT) provides much more information compared to non-enhanced CT images, especially for the differentiation of malignancies, such as liver carcinomas. Contrast media injection phase information is usually missing on public datasets and not standardized in the clinic even in the same region and language. This is a barrier to effective use of available CECT images in clinical research. The aim of this study is to detect contrast media injection phase from CT images by means of organ segmentation and machine learning algorithms. A total number of 2509 CT images split into four subsets of non-contrast (class #0), arterial (class #1), venous (class #2), and delayed (class #3) after contrast media injection were collected from two CT scanners. Seven organs including the liver, spleen, heart, kidneys, lungs, urinary bladder, and aorta along with body contour masks were generated by pre-trained deep learning algorithms. Subsequently, five first-order statistical features including average, standard deviation, 10, 50, and 90 percentiles extracted from the above-mentioned masks were fed to machine learning models after feature selection and reduction to classify the CT images in one of four above mentioned classes. A 10-fold data split strategy was followed. The performance of our methodology was evaluated in terms of classification accuracy metrics. The best performance was achieved by Boruta feature selection and RF model with average area under the curve of more than 0.999 and accuracy of 0.9936 averaged over four classes and 10 folds. Boruta feature selection selected all predictor features. The lowest classification was observed for class #2 (0.9888), which is already an excellent result. In the 10-fold strategy, only 33 cases from 2509 cases (∼1.4%) were misclassified. The performance over all folds was consistent. We developed a fast, accurate, reliable, and explainable methodology to classify contrast media phases which may be useful in data curation and annotation in big online datasets or local datasets with non-standard or no series description. Our model containing two steps of deep learning and machine learning may help to exploit available datasets more effectively.

CardSegNet: An adaptive hybrid CNN-vision transformer model for heart region segmentation in cardiac MRI

Cardiovascular MRI (CMRI) is a non-invasive imaging technique adopted for assessing the blood circulatory system’s structure and function. Precise image segmentation is required to measure cardiac parameters and diagnose abnormalities through CMRI data. Because of anatomical heterogeneity and image variations, cardiac image segmentation is a challenging task. Quantification of cardiac parameters requires high-performance segmentation of the left ventricle (LV), right ventricle (RV), and left ventricle myocardium from the background. The first proposed solution here is to manually segment the regions, which is a time-consuming and error-prone procedure. In this context, many semi- or fully automatic solutions have been proposed recently, among which deep learning-based methods have revealed high performance in segmenting regions in CMRI data. In this study, a self-adaptive multi attention (SMA) module is introduced to adaptively leverage multiple attention mechanisms for better segmentation. The convolutional-based position and channel attention mechanisms with a patch tokenization-based vision transformer (ViT)-based attention mechanism in a hybrid and end-to-end manner are integrated into the SMA. The CNN- and ViT-based attentions mine the short- and long-range dependencies for more precise segmentation. The SMA module is applied in an encoder-decoder structure with a ResNet50 backbone named CardSegNet. Furthermore, a deep supervision method with multi-loss functions is introduced to the CardSegNet optimizer to reduce overfitting and enhance the model’s performance. The proposed model is validated on the ACDC2017 (n=100), M&Ms (n=321), and a local dataset (n=22) using the 10-fold cross-validation method with promising segmentation results, demonstrating its outperformance versus its counterparts.

StellarPath: Hierarchical-vertical multi-omics classifier synergizes stable markers and interpretable similarity networks for patient profiling.

The Patient Similarity Network paradigm implies modeling the similarity between patients based on specific data. The similarity can summarize patients' relationships from high-dimensional data, such as biological omics. The end PSN can undergo un/supervised learning tasks while being strongly interpretable, tailored for precision medicine, and ready to be analyzed with graph-theory methods. However, these benefits are not guaranteed and depend on the granularity of the summarized data, the clarity of the similarity measure, the complexity of the network's topology, and the implemented methods for analysis. To date, no patient classifier fully leverages the paradigm's inherent benefits. PSNs remain complex, unexploited, and meaningless. We present StellarPath, a hierarchical-vertical patient classifier that leverages pathway analysis and patient similarity concepts to find meaningful features for both classes and individuals. StellarPath processes omics data, hierarchically integrates them into pathways, and uses a novel similarity to measure how patients' pathway activity is alike. It selects biologically relevant molecules, pathways, and networks, considering molecule stability and topology. A graph convolutional neural network then predicts unknown patients based on known cases. StellarPath excels in classification performances and computational resources across sixteen datasets. It demonstrates proficiency in inferring the class of new patients described in external independent studies, following its initial training and testing phases on a local dataset. It advances the PSN paradigm and provides new markers, insights, and tools for in-depth patient profiling.

DeFTA: A plug-and-play peer-to-peer decentralized federated learning framework

Federated learning (FL) is a pivotal catalyst for enabling large-scale privacy-preserving distributed machine learning (ML). By eliminating the need for local raw dataset sharing, FL substantially reduces privacy concerns and alleviates the isolated data problem. However, in reality, the success of FL is predominantly attributed to a centralized framework called FedAvg [1], in which workers are responsible for model training, and servers are in control of model aggregation. Nevertheless, FedAvg's centralized worker-server architecture has raised new concerns, including low scalability of the cluster, risk of data leakage, and central server failure or even defection. To overcome these challenges, we propose Decentralized Federated Trusted Averaging (DeFTA), a decentralized FL framework that serves as a plug-and-play replacement for FedAvg, bringing instant improvements to security, scalability, and fault-tolerance in the federated learning process. In essence, it primarily consists of a novel model aggregating formula with theoretical performance analysis, and a decentralized trust system (DTS) to significantly enhance system robustness. Extensive experiments conducted on six datasets and six basic models suggest that DeFTA not only exhibits comparable performance with FedAvg in a more realistic setting, but also achieves remarkable resilience even when 67% of workers are malicious.

Vision based intelligent traffic light management system using Faster R‐CNN

AbstractTransportation systems primarily depend on vehicular flow on roads. Developed countries have shifted towards automated signal control, which manages and updates signal synchronisation automatically. In contrast, traffic in underdeveloped countries is mainly governed by manual traffic light systems. These existing manual systems lead to numerous issues, wasting substantial resources such as time, energy, and fuel, as they cannot make real‐time decisions. In this work, we propose an algorithm to determine traffic signal durations based on real‐time vehicle density, obtained from live closed circuit television camera feeds adjacent to traffic signals. The algorithm automates the traffic light system, making decisions based on vehicle density and employing Faster R‐CNN for vehicle detection. Additionally, we have created a local dataset from live streams of Punjab Safe City cameras in collaboration with the local police authority. The proposed algorithm achieves a class accuracy of 96.6% and a vehicle detection accuracy of 95.7%. Across both day and night modes, our proposed method maintains an average precision, recall, F1 score, and vehicle detection accuracy of 0.94, 0.98, 0.96 and 0.95, respectively. Our proposed work surpasses all evaluation metrics compared to state‐of‐the‐art methodologies.

Houseplant leaf classification system based on deep learning algorithms

AbstractBotanical experts are typically relied upon to classify houseplants since even subtle differences in characteristics such as leaves can distinguish one species from another. Therefore, an automated system for recognizing houseplant leaves with accuracy and reliability becomes a valuable asset for the identification of indoor plant species. In this paper, a houseplant leaf classification system utilizing deep learning algorithms is proposed, which has been improved to effectively classify and identify a variety of houseplant leaf types. The system uses the ResNet-50 architecture based on convolutional neural network to analyze features of the leaf images and extract relevant information for classification. In addition, this work presents a newly constructed local dataset consisting of 2500 images to classify species of houseplant leaves. The dataset includes ten types of houseplant leaves that are suitable for cultivation in various climates at home. The dataset was augmented using data augmentation algorithms to increase its size and reduce overfitting. The developed system was training and testing using a local dataset. To evaluate the improved model, comparative experiments were conducted utilizing pre-trained models (original ResNet-50 and MobileNet_v2). The improved model revealed recognition accuracy of 99% with the augmented dataset and 98.60% without the augmentation, affirming its effectiveness. The improved model could potentially be used in various fields, including horticulture, plant pathology, and environmental monitoring to identify plant species.

CDEST: Class Distinguishability-Enhanced Self-Training Method for Adopting Pre-Trained Models to Downstream Remote Sensing Image Semantic Segmentation

The self-supervised learning (SSL) technique, driven by massive unlabeled data, is expected to be a promising solution for semantic segmentation of remote sensing images (RSIs) with limited labeled data, revolutionizing transfer learning. Traditional ‘local-to-local’ transfer from small, local datasets to another target dataset plays an ever-shrinking role due to RSIs’ diverse distribution shifts. Instead, SSL promotes a ‘global-to-local’ transfer paradigm, in which generalized models pre-trained on arbitrarily large unlabeled datasets are fine-tuned to the target dataset to overcome data distribution shifts. However, the SSL pre-trained models may contain both useful and useless features for the downstream semantic segmentation task, due to the gap between the SSL tasks and the downstream task. To adapt such pre-trained models to semantic segmentation tasks, traditional supervised fine-tuning methods that use only a small number of labeled samples may drop out useful features due to overfitting. The main reason behind this is that supervised fine-tuning aims to map a few training samples from the high-dimensional, sparse image space to the low-dimensional, compact semantic space defined by the downstream labels, resulting in a degradation of the distinguishability. To address the above issues, we propose a class distinguishability-enhanced self-training (CDEST) method to support global-to-local transfer. First, the self-training module in CDEST introduces a semi-supervised learning mechanism to fully utilize the large amount of unlabeled data in the downstream task to increase the size and diversity of the training data, thus alleviating the problem of biased overfitting of the model. Second, the supervised and semi-supervised contrastive learning modules of CDEST can explicitly enhance the class distinguishability of features, helping to preserve the useful features learned from pre-training while adapting to downstream tasks. We evaluate the proposed CDEST method on four RSI semantic segmentation datasets, and our method achieves optimal experimental results on all four datasets compared to supervised fine-tuning as well as three semi-supervised fine-tuning methods.

Improving urban CO2 spatial distribution modelling using multi-source data

Urban areas contribute approximately 70% of the total anthropogenic CO2 emissions, making them the primary focus of global carbon monitoring. However, accurate modelling of urban meteorology is challenging because of complex artificial landscapes. Reducing errors in urban meteorological simulation and improving the accuracy of modelling the spatial distribution of urban CO2 is of great significance for the “top-down” CO2 emissions estimation in urban areas. In this study, local urban datasets were constructed based on multiple data sources to overcome the limitation of insufficient information from a single data source. In the development of urban datasets, grid-by-grid data processing is realized, and the evaluation results show that the developed urban datasets are greatly improved compared with the default. The developed urban datasets were applied to WRF-Chem with 1-km spatial resolution, and the simulated column-averaged dry air mole fraction of CO2 (XCO2) was verified with the EM27/SUN observed data considering the slant observation path. The results show that urban datasets strongly influence the spatial distribution modelling of XCO2, depending on the state of the atmosphere near the surface, especially wind velocity. Accurate local urban datasets can effectively reduce the bias in urban XCO2 spatial distribution modelling and improve the capability of the atmospheric CO2 transport model in urban carbon emission estimation.

FedCAE: A New Federated Learning Framework for Edge-Cloud Collaboration Based Machine Fault Diagnosis

With the coming of the industrial big data era, data-driven fault diagnosis models emerge recently and show potential results in many studies. However, it is impractical to collect massive high-quality data in actual industrial applications, which strongly reduces the performance of fault diagnosis models. Therefore, multiple data owners are motivated to share their own data for training a brilliant model with the aggregated dataset. Notwithstanding, it is unrealistic to share data due to the potential conflict of interest. For addressing the issue of data island, a new federated framework namely FedCAE is proposed for fault diagnosis. In this framework, each client is equipped with a convolutional autoencoder (CAE) trained by its corresponding local data. Then, all CAEs are uploaded to a server and aggregated to a global CAE according to an adaptive weighted selection mechanism. Afterwards, the global CAE is downloaded to all clients for extracting low-level features from local datasets by its encoder and uploading these features to train a global fault diagnosis classifier in the server. At last, the classifier is downloaded to all clients for completing their own diagnosis tasks. Experiment results on two bearing datasets suggest FedCAE offers a promising solution on confidential decentralized learning.