30793 research outputs found
Sort by
Machine Learning-Based Electric Vehicle Charging Demand Forecasting: A Systematized Literature Review
Get PDFData Availability Statement:
The original contributions presented in the study are included in the article, further inquiries can be directed to the corresponding author.The transport sector significantly contributes to global greenhouse gas emissions, making electromobility crucial in the race toward the United Nations Sustainable Development Goals. In recent years, the increasing competition among manufacturers, the development of cheaper batteries, the ongoing policy support, and people’s greater environmental awareness have consistently increased electric vehicles (EVs) adoption. Nevertheless, EVs charging needs—highly influenced by EV drivers’ behavior uncertainty—challenge their integration into the power grid on a massive scale, leading to potential issues, such as overloading and grid instability. Smart charging strategies can mitigate these adverse effects by using information and communication technologies to optimize EV charging schedules in terms of power systems’ constraints, electricity prices, and users’ preferences, benefiting stakeholders by minimizing network losses, maximizing aggregators’ profit, and reducing users’ driving range anxiety. To this end, accurately forecasting EV charging demand is paramount. Traditionally used forecasting methods, such as model-driven and statistical ones, often rely on complex mathematical models, simulated data, or simplifying assumptions, failing to accurately represent current real-world EV charging profiles. Machine learning (ML) methods, which leverage real-life historical data to model complex, nonlinear, high-dimensional problems, have demonstrated superiority in this domain, becoming a hot research topic. In a scenario where EV technologies, charging infrastructure, data acquisition, and ML techniques constantly evolve, this paper conducts a systematized literature review (SLR) to understand the current landscape of ML-based EV charging demand forecasting, its emerging trends, and its future perspectives. The proposed SLR provides a well-structured synthesis of a large body of literature, categorizing approaches not only based on their ML-based approach, but also on the EV charging application. In addition, we focus on the most recent technological advances, exploring deep-learning architectures, spatial-temporal challenges, and cross-domain learning strategies. This offers an integrative perspective. On the one hand, it maps the state of the art, identifying a notable shift toward deep-learning approaches and an increasing interest in public EV charging stations. On the other hand, it uncovers underexplored methodological intersections that can be further exploited and research gaps that remain underaddressed, such as real-time data integration, long-term forecasting, and the development of adaptable models to different charging behaviors and locations. In this line, emerging trends combining recurrent and convolutional neural networks, and using relatively new ML techniques, especially transformers, and ML paradigms, such as transfer-, federated-, and meta-learning, have shown promising results for addressing spatial-temporality, time-scalability, and geographical-generalizability issues, paving the path for future research directions.This work was supported by the Office of Research, Zayed University under the Research Incentive Fund [grant number R23079]
Cutting Tool Remaining Useful Life Prediction Using Multi-Sensor Data Fusion Through Graph Neural Networks and Transformers
Get PDFData Availability Statement:
The data presented in this study are available in [CNC turning: Roughness, forces and tool wear] at [https://www.kaggle.com/datasets/adorigueto/cnc-turning-roughness-forces-and-tool-wear], reference number [42]. accessed on 16 March 2025.In the context of Industry 4.0 and smart manufacturing, predicting cutting tool remaining useful life (RUL) is crucial for enabling and enhancing the reliability and efficiency of CNC machining. This paper presents an innovative predictive model based on the data fusion architecture of Graph Neural Networks (GNNs) and Transformers to address the complexity of shallow multimodal data fusion, insufficient relational modeling, and single-task limitations simultaneously. The model harnesses time-series data, geometric information, operational parameters, and phase contexts through dedicated encoders, employs graph attention networks (GATs) to infer complex structural dependencies, and utilizes a cross-modal Transformer decoder to generate fused features. A dual-head output enables collaborative RUL regression and health state classification of cutting tools. Experiments are conducted on a multimodal dataset of 824 entries derived from multi-sensor data, constructing a systematic framework centered on tool flank wear width (VB), which includes correlation analysis, trend modeling, and risk assessment. Results demonstrate that the proposed model outperforms baseline models, with MSE reduced by 26–41%, MAE by 33–43%, R2 improved by 6–12%, accuracy by 6–12%, and F1-Score by 7–14%.This study was supported by the grant from the basic research projects of educational department of Liaoning province (Grant No. LJ212411035018)
Sleep-Related Disturbances, Psychosis, and Cognitive Decline in Healthy Older Adults: A Cross Sectional Analysis of PROTECT Study Data
Get PDFClinical Manifestations poster presentation at The Alzheimer’s Association International Conference (AAIC25), Toronto, Canada, 27-31 July 2025.BACKGROUND: Sleep-related disturbances are commonly reported in approximately 50% of older adults and have been associated with various psychiatric (e.g., psychosis) and neurodegenerative disorders (e.g., dementia). While the overlapping relationships between psychosis and sleep-related disturbances in cognitive impairment have been recognised for decades, the mediating role of subjective cognitive impairment (SCI) in the relationship between MBI-psychosis and sleep-related disturbance is poorly understood. This study, therefore, aimed to investigate the magnitude of MBI-psychosis on various sleep facets (i.e., sleep fragmentation, duration, inertia, quality, maintenance, satisfaction, daytime napping, deep sleep) while accounting for SCI in healthy UK-based 14,846 older adults (74.3% females; mean age: 63.15±7.44). METHOD: All participants were recruited from the general population and completed a range of online self-report measures on sleep, MBI-psychosis, SCI. Linear regression was used to analyse the relationship between MBI-psychosis and sleep; mediation analysis examined the effects of SCI on this relationship. RESULT: The findings demonstrated significant yet small-sized correlations between MBI-psychosis, SCI, and all sleep facets (p < 0.001). While MBI-psychosis had a direct significant effect on all sleep facets; SCI also partially mediated the psychosis-sleep relationship (p < 0.001). However, after controlling for depression, anxiety, and sex, the direct effect of psychosis on sleep was limited to sleep duration, daytime napping, and sleep onset. At the same time, SCI was found to fully mediate the relationship of psychosis with deep sleep, sleep fragmentation, inertia, quality, satisfaction and maintenance; SCI also partially mediated the relationship of psychosis with sleep onset and duration (all β<0.2). CONCLUSION: These findings highlight the importance of early identification of sleep-related disturbances and associated comorbid disorders, including depression and anxiety, in middle-aged and older adults as a preventative strategy for cognitive decline and the onset of dementia
Simultaneous State and Fault Estimation over Bandwidth-Constrained Networks: A Relay-Aided Binary Encoding Strategy
Get PDFThis paper is concerned with the joint state and fault estimation problem for a class of discrete-time systems over a bandwidth-constrained network subject to actuator and sensor faults. The signal attenuation is resisted by locating the amplify-and-forward relay between the sensor and the estimator. In the sensor-to-relay channel, a binary encoding mechanism is employed to encode the measurement signal into a series of binary numbers. The random bit error, governed by a series of Bernoulli distributed random variables, is considered due to long-distance transmission and channel noise. The objective of the problem addressed in this paper is to design a joint state and fault estimator by augmenting the system state and the sensor fault into a descriptor system model. Sufficient conditions are established to ensure that the joint estimation error is exponentially bounded in the mean-square sense. The desired joint estimator gain is parameterized based on the solution of certain matrix inequalities. Finally, a numerical simulation is provided to validate the effectiveness of the proposed joint estimator design method
KDET-HPFL: A Personalized Federated Learning Framework for Multimodal Pedestrian Detection With Adaptive Feature Selection
Get PDFPedestrian detection plays a critical role in intelligent perception systems in autonomous vehicles, which directly influences the reliability and safety of the overall system. Advanced in-vehicle sensor technology has enabled the continuous evolution of pedestrian detection systems by leveraging heterogeneous multimodal inputs such as RGB, infrared, depth, Light Detection And Ranging, and event data. Nevertheless, establishing a robust pedestrian detection system that is capable of integrating and processing such heterogeneous multimodal data effectively remains a significant challenge. At the same time, growing concerns about data privacy among automobile manufacturers have hindered further advances in detection model performance by restricting the sharing of private data within the industry. In this paper, a novel personalised federated learning framework, Kolmogorov-Arnold network-based Dual Expert Transformer Heterogeneous Personalized Federated Learning (KDET-HPFL), is proposed for multimodal pedestrian detection. To be specific, the KDET pedestrian detector is developed based on an expert feature selection module (which is designed to adaptively choose essential features from multimodal data) and a Group-Rational Kolmogorov-Arnold Network module, which enhances the feature extraction capabilities and improves the detection performance effectively. The HPFL framework is proposed for data privacy protection on heterogeneous multimodal data, where a cross-client aggregation (CCA) method is put forward by integrating different aggregation methods for certain layers in the KDET detector. With CCA, the HPFL framework achieves personalised feature retention of multimodal data pairs on multiple clients and improved model aggregation effect for each client. Experimental findings reveal that the proposed KDET-HPFL framework outperforms some existing personalised federated learning frameworks for pedestrian detection on four public datasets (i.e., LLVIP, STCrowd, InOutDoor, and EventPed) with mAP scores of 73.74%, 75.39%, 66.14%, and 79.57%, respectively
Data-driven modelling of N₂O production in wastewater processes using neural ordinary differential equations
No full textHIGHLIGHTS:
• Captured the underlying dynamics of typical activated sludge processes, focusing on N2O production, using neural ordinary differential equation (NODE) models.
• Developed a normalisation method for efficient training of stiff NODE models.
• Extended NODE training algorithms to incorporate exogenous inputs.Data Availability Statement:
All relevant data are available from an online repository or repositories: https://github.com/Xiangjun-Huang/NODE_BSM1.git.Supplementary data are available online at: https://iwaponline.com/wst/article/doi/10.2166/wst.2026.231/110930/Data-driven-modelling-of-N2O-production-in#supplementary-data .Modelling nitrous oxide (N₂O) production in wastewater treatment processes presents greater challenges than for other components, owing to its multiple production pathways and pronounced spatiotemporal variations. This study proposes a novel data-driven approach employing neural ordinary differential equations (NODEs) to capture the intrinsic dynamics of N₂O production in typical activated sludge processes. The NODE models are trained directly on state trajectory data, which incorporate continuous influent variations and operational adjustments as external forcings to the system dynamics. To address these external influences, we extend standard training procedures. In addition, a normalisation technique and an incremental strategy are introduced to enhance the computational efficiency of NODE implementation in stiff wastewater systems. This methodology is validated using simulated data from the benchmark simulation model no. 1 (BSM1) plant, adapted to integrate the activated sludge model for greenhouse gases no. 1 (ASMG1). Results demonstrate the efficacy of NODE-based approach in accurately capturing the complex dynamics governing N₂O production, highlighting its potential for controlling and mitigating greenhouse gases emissions in wastewater treatment.The work was supported by the CRONUS project (grant agreement ID: 101084405) funded by the European Union under Horizon Europe Research and Innovation Action scheme
Semantic-Aware Cooperative Communication and Computation Framework in Vehicular Networks
Get PDFSemantic Communication (SC) combined with Vehicular edge computing (VEC) provides an efficient edge task processing paradigm for Internet of Vehicles (IoV). Focusing on highway scenarios, this paper proposes a Tripartite Cooperative Semantic Communication (TCSC) framework, which enables Vehicle Users (VUs) to perform semantic task offloading via Vehicle-to-Infrastructure (V2I) and Vehicle-to-Vehicle (V2V) communications. Considering task latency and the number of semantic symbols, the framework constructs a Mixed-Integer Nonlinear Programming (MINLP) problem, which is transformed into two subproblems. First, we innovatively propose a multi-agent proximal policy optimization task offloading optimization method based on parametric distribution noise (MAPPO-PDN) to solve the optimization problem of the number of semantic symbols; second, linear programming (LP) is used to optimize the offloading ratio. Simulations show that performance of this scheme is superior to that of other algorithms.This work was supported in part by Jiangxi Province Science and Technology Development Programme under Grant 20242BCC32016; in part by the National Natural Science Foundation of China under Grant 61701197; in part by Basic Research Program of Jiangsu under Grant BK20252084; in part by the National Key Research and Development Program of China under Grant 2021YFA1000500(4) and in part by the 111 Project under Grant B23008
Observation of Λ Hyperon Local Polarization in Pb Collisions at √<sub>NN</sub> = 8.16 TeV
No full textA version of the article is available at arXiv:2502.07898v2 [nucl-ex] (https://arxiv.org/abs/2502.07898). Comments: Replaced with the published version. Added the journal reference and the DOI. All the figures and tables can be found at https://cms-results.web.cern.ch/cms-results/public-results/publications/HIN-24-002 (CMS Public Pages). Report number: CMS-HIN-24-002, CERN-EP-2024-328. Journal reference: Phys. Rev. Lett. 135 (2025) 132301. Submission history: From: The CMS Collaboration: [v1] Tue, 11 Feb 2025 19:09:55 UTC (556 KB); [v2] Wed, 1 Oct 2025 12:27:55 UTC (557 KB).Data availability—
Release and preservation of data used by the CMS Collaboration as the basis for publications is guided by the CMS data preservation, reuse, and open access policy [79]. CMS data availability statement, 10.7483/OPENDATA.CMS.1BNU.8V1W .The polarization of the Λ and ¯Λ hyperons along the beam direction has been measured in proton-lead (-Pb) collisions at a center-of-mass energy per nucleon pair of 8.16 TeV. The data were obtained with the CMS detector at the LHC and correspond to an integrated luminosity of 186.0 ± 6.5 nb⁻¹. A significant azimuthal dependence of the hyperon polarization, characterized by the second-order Fourier sine coefficient ,s2, is observed. The ,s2 values decrease as a function of charged particle multiplicity, but increase with transverse momentum. A hydrodynamic model that describes the observed ,s2 values in nucleus-nucleus collisions by introducing vorticity effects does not reproduce either the sign or the magnitude of the -Pb results. These observations pose a challenge to the current theoretical implementation of spin polarization in heavy ion collisions and offer new insights into the origin of spin polarization in hadronic collisions at LHC energies.SCOAP³
Optimising electric vehicle charging stations on UK motorways using deep neural networks: A scenario-based case study of the M40
Get PDFThe UK’s electric vehicle (EV) adoption is accelerating rapidly, with over 1.4 million EVs on the road and projections reaching 14 million by 2030. However, while approximately 75,000 public chargers have been installed to date, this remains far short of the govern-ment’s 300,000 target by 2030. Planning adequate infrastructure involves more than fore-casting national demand—it requires estimating the number of chargers needed in specific locations, such as motorway corridors, while accounting for traffic volumes, grid capacity, and funding limitations. Most existing approaches rely on linear models that fail to capture the full complexity and interdependence of these factors.
This study proposes a predictive framework using Deep Neural Networks (DNNs) to estimate the number of ultra-fast EV charging stations required under varying planning conditions and constraints. Unlike traditional methods, the DNN model learns nonlinear relationships across ten key input features, integrating both technical variables (e.g., traffic flow, substation capacity, energy consumption) and policy-relevant constraints (e.g., budgets, installation costs). A scenario-based case study was conducted on the M40 motorway to demonstrate the model’s flexibility in real world contexts—covering Crowded, Energy Constrained, Budget-Constrained, and Balanced scenarios using actual traffic, charger, and substation data. The results show that this DNN-based approach offers a scalable, data informed planning tool that can support UK policymakers in making more resilient and adaptive infrastructure decisions
Data sources:
Access Repository Dashboard
Do you manage Open Research Online? Become a CORE Member to access insider analytics, issue reports and manage access to outputs from your repository in the CORE Repository Dashboard! 👇