Search Results for author:
Found 63 papers, 14 papers with code
Continual Learning for Smart City: A Survey
We believe this survey can help relevant researchers quickly familiarize themselves with the current state of continual learning research used in smart city development and direct them to future research trends.
Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning
We conduct a series of experiments to prove LLMs can obtain benefits from mistakes in both directions.
Self-supervised Contrastive Learning for Implicit Collaborative Filtering
Contrastive learning-based recommendation algorithms have significantly advanced the field of self-supervised recommendation, particularly with BPR as a representative ranking prediction task that dominates implicit collaborative filtering.
A Survey of Route Recommendations: Methods, Applications, and Opportunities
Our survey offers a comprehensive review of route recommendation work based on urban computing.
Uncertainty-Aware Transient Stability-Constrained Preventive Redispatch: A Distributional Reinforcement Learning Approach
In this paper, a Graph neural network guided Distributional Deep Reinforcement Learning (GD2RL) method is proposed, for the first time, to solve the uncertainty-aware transient stability-constrained preventive redispatch problem.
Distributional Reinforcement Learning
reinforcement-learning
Learning Contrastive Feature Representations for Facial Action Unit Detection
To address the challenge posed by noisy AU labels, we augment the supervised signal through the introduction of a self-supervised signal.
LF Tracy: A Unified Single-Pipeline Approach for Salient Object Detection in Light Field Cameras
Previous approaches predominantly employ a custom two-stream design to discover the implicit angular feature within light field cameras, leading to significant information isolation between different LF representations.
Pricing of Short Circuit Current in High IBR-Penetrated System
With the growing penetration of Inverter-Based Resources (IBRs) in power systems, stability service markets have emerged to incentivize technologies that ensure power system stability and reliability.
Decision-Oriented Learning for Future Power System Decision-Making under Uncertainty
This paper first elaborates on the mismatch between more accurate forecasts and more optimal decisions in the power system caused by statistical-based learning (SBL) and explains how DOL resolves this problem.
Learning Time-aware Graph Structures for Spatially Correlated Time Series Forecasting
Spatio-temporal forecasting of future values of spatially correlated time series is important across many cyber-physical systems (CPS).
E2E-AT: A Unified Framework for Tackling Uncertainty in Task-aware End-to-end Learning
Successful machine learning involves a complete pipeline of data, model, and downstream applications.
ULMA: Unified Language Model Alignment with Human Demonstration and Point-wise Preference
Aligning language models to human expectations, e. g., being helpful and harmless, has become a pressing challenge for large language models.
Out-of-Distribution Generalized Dynamic Graph Neural Network for Human Albumin Prediction
We first model human albumin prediction as a dynamic graph regression problem to model the dynamics and patient relationship.
Managing the Uncertainty in System Dynamics Through Distributionally Robust Stability-Constrained Optimization
To address this issue, a propagation mechanism from the uncertainty of the system dynamic parameters to the stability constraint coefficients is established.
Cyber Recovery from Dynamic Load Altering Attacks: Linking Electricity, Transportation, and Cyber Networks
To address the increasing vulnerability of power grids, significant attention has been focused on the attack detection and impact mitigation.
Task-Aware Machine Unlearning and Its Application in Load Forecasting
To balance between unlearning completeness and model performance, a performance-aware algorithm is proposed by evaluating the sensitivity of local model parameter change using influence function and sample re-weighting.
Semi-Supervised Dual-Stream Self-Attentive Adversarial Graph Contrastive Learning for Cross-Subject EEG-based Emotion Recognition
In this paper, a semi-supervised Dual-stream Self-Attentive Adversarial Graph Contrastive learning framework (termed as DS-AGC) is proposed to tackle the challenge of limited labeled data in cross-subject EEG-based emotion recognition.
Control-mode as a Grid Service in Software-defined Power Grids: GFL vs GFM
In power systems with high penetration of power electronics, grid-forming control is proposed to replace traditional Grid-Following Converter (GFL) in order to improve the overall system strength and resist small-signal instability in weak grids by directly forming the terminal voltage.
OAFuser: Towards Omni-Aperture Fusion for Light Field Semantic Segmentation
To avoid feature loss during network propagation and simultaneously streamline the redundant information from the light field camera, we present a simple yet very effective Sub-Aperture Fusion Module (SAFM) to embed sub-aperture images into angular features without any additional memory cost.
Stability Constrained Optimization in High IBR-Penetrated Power Systems-Part I: Constraint Development and Unification
To ensure system stability during system operation and to provide appropriate incentives in the future market-based stability maintenance framework, it is essential to develop a comprehensive set of power system stability constraints which can be incorporated into system operation, market design and planning problems.
Stability Constrained Optimization in High IBR-Penetrated Power Systems-Part II: Constraint Validation and Applications
Multiple operational constraints of power system stability are derived analytically and reformulated into Second-Order Cone (SOC) form through a unification method in Part I of this paper.
Benchmarking Explanatory Models for Inertia Forecasting using Public Data of the Nordic Area
This paper investigates the performance of a day-ahead explanatory model for inertia forecasting based on field data in the Nordic system, which achieves a 43% reduction in mean absolute percentage error (MAPE) against a state-of-the-art time-series forecast model.
Vehicle-to-grid plug-in forecasting for participation in ancillary services markets
Electric vehicle (EV) charge points (CPs) can be used by aggregators to provide frequency response (FR) services.
Enhancing Cyber-Resiliency of DER-based SmartGrid: A Survey
The overall aim of this survey is to demonstrate the development trend of CRE methods and motivate further efforts to improve the cyber-resiliency of DER-based smart grid.
On the 1-Wasserstein Distance between Location-Scale Distributions and the Effect of Differential Privacy
The effect of differential privacy using the Laplace and Gaussian mechanisms on the 1-Wasserstein distance is studied using the closed-form expressions and bounds.
Optimal Design of Neural Network Structure for Power System Frequency Security Constraints
Recently, frequency security is challenged by high uncertainty and low inertia in power system with high penetration of Renewable Energy Sources (RES).
Always Strengthen Your Strengths: A Drift-Aware Incremental Learning Framework for CTR Prediction
Streaming data has the characteristic that the underlying distribution drifts over time and may recur.
Risk-Aware Objective-Based Forecasting in Inertia Management
The objective-based forecasting considers the asymmetric and non-linear impacts of forecasting errors on decision objectives, thus improving the effectiveness of its downstream decision-making process.
Preventive-Corrective Cyber-Defense: Attack-Induced Region Minimization and Cybersecurity Margin Maximization
With any given cyber-defense resource, this paper proposes a preventive-corrective cyber-defense strategy, which minimizes the FDI attack-induced region in a preventive manner, followed by maximizing the cybersecurity margin in a corrective manner.
Availability Adversarial Attack and Countermeasures for Deep Learning-based Load Forecasting
To tackle this attack, an adversarial training algorithm is proposed.
Scheduling of Software-Defined Microgrids for Optimal Frequency Regulation
Integrated with a high share of Inverter-Based Resources (IBRs), microgrids face increasing complexity of frequency dynamics, especially after unintentional islanding from the maingrid.
Design and Planning of Flexible Mobile Micro-Grids Using Deep Reinforcement Learning
The results on a case study for ger communities in Mongolia suggest that mobile nomadic energy systems can be both technically and economically feasible, particularly when considering flexibility, although the degree of spatial dispersion among households is an important limiting factor.
Cyber-physical interdependent restoration scheduling for active distribution network via ad hoc wireless communication
This paper proposes a post-disaster cyber-physical interdependent restoration scheduling (CPIRS) framework for active distribution networks (ADN) where the simultaneous damages on cyber and physical networks are considered.
V-Cloak: Intelligibility-, Naturalness- & Timbre-Preserving Real-Time Voice Anonymization
Apart from the anonymity loss, we further incorporate the intelligibility loss and the psychoacoustics-based naturalness loss.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Towards Joint Electricity and Data Trading: A Scalable Cooperative Game Theoretic Approach
This paper, for the first time, proposes a joint electricity and data trading mechanism based on cooperative game theory.
Federated Graph-based Networks with Shared Embedding
Nowadays, user privacy is becoming an issue that cannot be bypassed for system developers, especially for that of web applications where data can be easily transferred through internet.
A Wireless-Assisted Hierarchical Framework to Accommodate Mobile Energy Resources
The societal decarbonisation fosters the installation of massive renewable inverter-based resources (IBRs) in replacing fossil fuel based traditional energy supply.
A Missing Value Filling Model Based on Feature Fusion Enhanced Autoencoder
We first incorporate into an autoencoder a hidden layer that consists of de-tracking neurons and radial basis function neurons, which can enhance the ability of learning interrelated features and common features.
Localization of Coordinated Cyber-Physical Attacks in Power Grids Using Moving Target Defense and Deep Learning
As one of the most sophisticated attacks against power grids, coordinated cyber-physical attacks (CCPAs) damage the power grid's physical infrastructure and use a simultaneous cyber attack to mask its effect.
Blending Data and Physics Against False Data Injection Attack: An Event-Triggered Moving Target Defence Approach
However, the uncontrollable false positive rate of the data-driven detector and the extra cost of frequent MTD usage limit their wide applications.
Mitigation of Cyberattacks through Battery Storage for Stable Microgrid Operation
In this paper, we present a mitigation methodology that leverages battery energy storage system (BESS) resources in coordination with microgrid (MG) ancillary services to maintain power system operations during cyberattacks.
On the Adaptation to Concept Drift for CTR Prediction
Click-through rate (CTR) prediction is a crucial task in web search, recommender systems, and online advertisement displaying.
Cyber-Physical Risk Assessment for False Data Injection Attacks Considering Moving Target Defences
In this paper, we examine the factors that influence the success of false data injection (FDI) attacks in the context of both cyber and physical styles of reinforcement.
Frequency Response from Aggregated V2G Chargers With Uncertain EV Connections
Fast frequency response (FR) is highly effective at securing frequency dynamics after a generator outage in low inertia systems.
HiSTGNN: Hierarchical Spatio-temporal Graph Neural Networks for Weather Forecasting
In this paper, we propose a novel Hierarchical Spatio-Temporal Graph Neural Network (HiSTGNN) to model cross-regional spatio-temporal correlations among meteorological variables in multiple stations.
Value of Fleet Vehicle Grid in Providing Transmission System Operator Services
In this paper a new aggregated model for electric vehicle (EV) fleets is presented that considers their daily and weekly usage patterns.
Voltage Stability Constrained Unit Commitment in High IBG-Penetrated Power Systems
Based on this, an optimal system scheduling model is proposed to minimize the overall system operation cost while maintaining the voltage stability during normal operation through dynamically optimizing the active and reactive power output from IBGs.
Robust Moving Target Defence Against False Data Injection Attacks in Power Grids
Recently, moving target defence (MTD) has been proposed to thwart false data injection (FDI) attacks in power system state estimation by proactively triggering the distributed flexible AC transmission system (D-FACTS) devices.
Fixed-Time Convergent Distributed Observer Design of Linear Systems: A Kernel-Based Approach
The robust distributed state estimation for a class of continuous-time linear time-invariant systems is achieved by a novel kernel-based distributed observer, which, for the first time, ensures fixed-time convergence properties.
A Resilience-Oriented Centralised-to-Decentralised Framework for Networked Microgrids Management
This paper proposes a cyber-physical cooperative mitigation framework to enhance power systems resilience under extreme events, e. g., earthquakes and hurricanes.
Frequency-Constrained Resilient Scheduling of Microgrid: A Distributionally Robust Approach
In order to prevent the potential frequency instability due to the high Power Electronics (PE) penetration under an unintentional islanding event, this paper presents a novel microgrid scheduling model which explicitly models the system frequency dynamics as well as the long/short term uncertainty associated with renewable energy resources and load.
Cyber-Resilient Self-Triggered Distributed Control of Networked Microgrids Against Multi-Layer DoS Attacks
Networked microgrids with high penetration of distributed generators have ubiquitous remote information exchange, which may be exposed to various cyber security threats.
Probabilistic Scheduling of UFLS to Secure Credible Contingencies in Low Inertia Systems
The reduced inertia levels in low-carbon power grids necessitate explicit constraints to limit frequency's nadir and rate of change during scheduling.
Topology Learning Aided False Data Injection Attack without Prior Topology Information
False Data Injection (FDI) attacks against powersystem state estimation are a growing concern for operators. Previously, most works on FDI attacks have been performedunder the assumption of the attacker having full knowledge ofthe underlying system without clear justification.
An Explainable CNN Approach for Medical Codes Prediction from Clinical Text
Our approach substantially outperforms previous results on top-50 medical code prediction on MIMIC-III dataset.
Towards Optimal Coordination between Regional Groups: HVDC Supplementary Power Control
With Europe dedicated to limiting climate change and greenhouse gas emissions, large shares of Renewable Energy Sources (RES) are being integrated in the national grids, phasing out conventional generation.
A Deep Learning based Detection Method for Combined Integrity-Availability Cyber Attacks in Power System
As one of the largest and most complex systems on earth, power grid (PG) operation and control have stepped forward as a compound analysis on both physical and cyber layers which makes it vulnerable to assaults from economic and security considerations.
Enhanced Cyber-Physical Security Using Attack-resistant Cyber Nodes and Event-triggered Moving Target Defence
In this context, a distributed event-triggered MTD protocol is implemented at the physical layer to complement cyber side enhancement.
Conditions for Regional Frequency Stability in Power System Scheduling -- Part II: Application to Unit Commitment
In Part I of this paper we have introduced the closed-form conditions for guaranteeing regional frequency stability in a power system.
Optimization and Control Systems and Control Systems and Control
Conditions for Regional Frequency Stability in Power System Scheduling -- Part I: Theory
This is the first reported mathematical framework with explicit conditions to maintain frequency stability in a power system exhibiting inter-area oscillations in frequency.
Optimization and Control Systems and Control Systems and Control
Value of Point-of-load Voltage Control for Enhanced Frequency Response in Future GB Power System
The need for Enhanced Frequency Response (EFR) is expected to increase significantly in future low-carbon Great Britain (GB) power system.
Efficient Calculation of Crossing Symmetric BCJ Tree Numerators
In this paper, we propose an improved method for directly calculating double-copy-compatible tree numerators in (super-)Yang-Mills and Yang-Mills-scalar theories.
High Energy Physics - Theory
A deep learning-based remaining useful life prediction approach for bearings
In industrial applications, nearly half the failures of motors are caused by the degradation of rolling element bearings (REBs).
