1,721,125 research outputs found
Eco-FL: Enhancing Federated Learning sustainability in edge computing through energy-efficient client selection
No full textIn the realm of edge cloud computing (ECC), Federated Learning (FL) revolutionizes the decentralization of machine learning (ML) models by enabling their training across multiple devices. In this way, FL preserves privacy and minimizes the need for centralized data by processing data near the source. From a communication standpoint, only the model weights are exchanged between devices. By avoiding the need to send data to a centralized location for processing, FL reduces the energy required for data transfer and supports more efficient use of computing resources at the edge. FL is particularly advantageous for resource-constrained devices, such as smartphones and IoT devices. However, this limited computational power and battery capacity and the challenge of energy consumption are critical aspects of FL systems. This paper introduces Eco-FL, an innovative methodology designed to optimize energy consumption in FL systems, in the field of Green Edge Cloud Computing (GECC). Our approach employs a device selection process that considers the entropy of the data held by the devices and their available energy reserves. This ensures that devices with lower energy availability are less likely to participate in the training rounds, prioritizing those with higher energy capacities. To evaluate the efficacy of our methodology, we utilize FedEntropy, an entropy-based aggregation method, alongside established aggregation methods such as FedAvg and FedProx for performance comparison. The effectiveness of Eco-FL in reducing energy consumption without compromising the accuracy of the FL process is demonstrated through analyses conducted on three distinct datasets. These analyses vary the β parameter of the Dirichlet distribution and account for scenarios with both homogeneous and heterogeneous initial device charges. Our findings validate Eco-FL's potential to enhance the sustainability of FL systems by judiciously managing client participation based on energy criteria, presenting a significant step forward in the development of energy-efficient FL
A data-driven artificial neural network model for the prediction of ground motion from induced seismicity: The case of The Geysers geothermal field
No full textGround-motion models have gained foremost attention during recent years for being capable of predicting ground-motion intensity levels for future seismic scenarios. They are a key element for estimating seismic hazard and always demand timely refinement in order to improve the reliability of seismic hazard maps. In the present study, we propose a ground motion prediction model for induced earthquakes recorded in The Geysers geothermal area. We use a fully connected data-driven artificial neural network (ANN) model to fit ground motion parameters. Especially, we used data from 212 earthquakes recorded at 29 stations of the Berkeley–Geysers network between September 2009 and November 2010. The magnitude range is 1.3 and 3.3 moment magnitude (Mw), whereas the hypocentral distance range is between 0.5 and 20 km. The ground motions are predicted in terms of peak ground acceleration (PGA), peak ground velocity (PGV), and 5% damped spectral acceleration (SA) at T=0.2, 0.5, and 1 s. The predicted values from our deep learning model are compared with observed data and the predictions made by empirical ground motion prediction equations developed by Sharma et al. (2013) for the same data set by using the nonlinear mixed-effect (NLME) regression technique. For validation of the approach, we compared the models on a separate data made of 25 earthquakes in the same region, with magnitudes ranging between 1.0 and 3.1 and hypocentral distances ranging between 1.2 and 15.5 km, with the ANN model providing a 3% improvement compared to the baseline GMM model. The results obtained in the present study show a moderate improvement in ground motion predictions and unravel modeling features that were not taken into account by the empirical model. The comparison is measured in terms of both the R2 statistic and the total standard deviation, together with inter-event and intra-event components
Integrating Object Detection and Advanced Analytics for Smart City Crowd Management
No full textIn the context of rapidly advancing smart cities, efficient crowd analysis plays a crucial role in ensuring public safety, urban planning, and resource management. This paper presents a novel framework that combines the popular You Only Look Once (YOLO) object detection algorithm with advanced crowd analysis techniques, aiming to improve the understanding and management of urban crowd dynamics. The proposed framework leverages YOLO's real-time object detection capabilities to detect various objects within video frames, with a particular focus on identifying individuals. To initiate the crowd analysis process, the detected persons are isolated and tracked over time, enabling the collection of valuable data for comprehensive crowd behavior analysis. By leveraging this rich dataset, the framework enables the extraction of key crowd characteristics, such as crowd density, crowd flow patterns, crowd distribution, and crowd congestion levels. Moreover, the framework incorporates techniques to analyze the extracted data, offering valuable insights into crowd dynamics
Predictive Analytics for Smart Parking: A Deep Learning Approach in Forecasting of IoT Data
No full textNowadays, a sustainable and smart city focuses on energy efficiency and the reduction of polluting emissions through smart mobility projects and initiatives to "sensitize"infrastructure. Smart parking is one of the building blocks of intelligent mobility, innovative mobility that aims to be flexible, integrated, and sustainable and consequently integrated into a Smart City. By using the Internet of Things (IoT) sensors located in the parking areas or the underground car parks in combination with a mobile application, which indicates to citizens the free places in the different areas of the city and guides them toward the chosen parking, it is possible to reduce air pollution and fluidifying noise traffic. In this article, we present and discuss an innovative Deep Learning-based ensemble technique in forecasting the parking space occupancy to reduce the search time for parking and to optimize the flow of cars in particularly congested areas, with an overall positive impact on traffic in urban centres. A genetic algorithm has also been used to optimize predictors parameters. The main goal is to design an intelligent IoT-based service that can predict, in the next few hours, the parking spaces occupancy of a street. The proposed approach has been assessed on a real IoT dataset composed by over than 15M of collected sensor records. Obtained results demonstrate that our method outperforms both single predictors and the widely used strategy of the mean providing inherently robust predictions
FL-Enhance: A federated learning framework for balancing non-IID data with augmented and shared compressed samples
No full textFederated Learning (FL), which enables multiple clients to cooperatively train global models without revealing private data, has gained significant attention from researchers in recent years. However, the data samples on each participating device in FL are often not independent and identically distributed (IID), leading to significant statistical heterogeneity challenges. In this paper, we propose FL-Enhance, a novel framework to address the non-IID-ness data issue in FL by leveraging established solutions such as data selection, data compression, and data augmentation. FL-Enhance, specifically, utilizes cGANs that are trained locally on the server level, which represents a relatively novel approach within the FL framework. Also, data compression techniques are applied to preserve privacy during data sharing between clients and servers. We compare our framework with the commonly used SMOTE data augmentation technique and test it with different FL algorithms, including FedAvg, FedNova, and FedOpt. We conducted experiments using both image and tabular data to evaluate the effectiveness of our proposed framework. The experimental findings show that FL-Enhance can substantially enhance the performance of the trained models in situations of severe pathological clients while still preserving privacy, which is the fundamental requirement in the FL context
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
A deep learning approach for facility patient attendance prediction based on medical booking data
No full textNowadays, data-driven methodologies based on the clinical history of patients represent a promising research field in which personalized and intelligent healthcare systems can be opportunely designed and developed. In this perspective, Machine Learning (ML) algorithms can be efficiently adopted to deploy smart services to enhance the overall quality of healthcare systems. In this work, starting from an in-depth analysis of a data set composed of millions of medical booking records collected from the public healthcare organization in the region of Campania, Italy, we have developed a predictive model to extract useful knowledge on patients, medical staff, and related healthcare structures. In more detail, the main contribution is to suggest a Deep Learning (DL) methodology able to predict the access of a patient in one or more medical facilities of a fixed set in the immediate future, the subsequent 2 months. A structured Temporal Convolutional Neural Network (TCNN) is designed to extract temporal patterns from the administrative medical history of a patient. The experiment shows the goodness of the designed methodology. Finally, this work represents a novel application of a TCNN model to a multi-label classification problem not linked to text categorization or image recognition
Unsupervised Learning for Depth Estimation in Unstructured Environments
No full textEnvironment perception through deep computation in unstructured environments is important for the construction of autonomous navigation systems. Most research focuses on navigation in structured scenes, including indoor mobility and driving along roads, while neglecting to consider unstructured environments, which often contain diverse heights and distributions. In addition, existing depth estimation algorithms based on deep learning often need to complete training under the supervision of Ground truth, and GT data with a large number of labels are not always easy to obtain. To tackle this issue, this paper proposes an unsupervised stereo depth estimation method for processing UAV navigation images in an unstructured environment. The method contains a primitive U-shaped CNN network architecture for processing such scenes. The feature extraction layer of the network is based on the YOLOv3 residual structure, and additional attention modules help the network enhance its ability to perceive image features. Finally, depth estimation experiments on the unstructured environments dataset Mid-Air further demonstrate the effectiveness and reliability of the proposed method
Investigating Random Variations of the Forward-Forward Algorithm for Training Neural Networks
No full textThe Forward-forward (FF) algorithm is a new method for training neural networks, proposed as an alternative to the traditional Backpropagation (BP) algorithm by Hinton. The FF algorithm replaces the backward computations in the learning process with another forward pass. Each layer has an objective function, which aims to be high for positive data and low for negative ones. This paper presents a preliminary investigation into variations of the FF algorithm, such as incorporating a local Backpropagation to create a hybrid network that robustly converges while preserving the ability to avoid backward computations when needed, for example, in non-differentiable areas of the network. Additionally, a pseudo-random logic for selecting trainable stacks of layers at each epoch is proposed to speed up the learning process
- …
