检索结果-内蒙古大学图书馆

A Graph Neural Network Multi-Task Learning-Based Approach for Detection and Localization of Cyberattacks in Smart Grids

学校读者我要写书评

暂无评论

A Graph Neural Network Multi-Task Learning-Based Approach fo...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Abdulrahman Takiddin Rachad Atat Muhammad Ismail Katherine Davis Erchin Serpedin Department of Electrical & Computer Engineering Texas A&M University College Station TX USA Electrical & Computer Engineering Program Texas A&M University at Qatar Doha Qatar Department of Computer Science Tennessee Technological University Cookeville TN USA

False data injection attacks (FDIAs) on smart power grids’ measurement data present a threat to system stability. When malicious entities launch cyberattacks to manipulate the measurement data, different grid components will be affected, which leads to failures. For effective attack mitigation, two tasks are required: determining the status of the system (normal operation/under attack) and localizing the attacked bus/power substation. Existing mitigation techniques carry out these tasks separately and offer limited detection performance. In this paper, we propose a multi-task learning-based approach that performs both tasks simultaneously using a graph neural network (GNN) with stacked convolutional Chebyshev graph layers. Our results show that the proposed model presents superior system status identification and attack localization abilities with detection rates of 98.5−100% and 99 − 100%, respectively, presenting improvements of 5 − 30% compared to benchmarks.

关键词： Location awareness Convolution Power system stability Chebyshev approximation Benchmark testing Multitasking Graph neural networks

Adversarial Environment Design via Regret-Guided Diffusion Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chung, Hojun Lee, Junseo Kim, Minsoo Kim, Dohyeong Oh, Songhwai Interdisciplinary Program in Artificial Intelligence and ASRI Seoul National University Korea Republic of Department of Electrical and Computer Engineering and ASRI Seoul National University Korea Republic of

Training agents that are robust to environmental changes remains a significant challenge in deep reinforcement learning (RL). Unsupervised environment design (UED) has recently emerged to address this issue by generating a set of training environments tailored to the agent’s capabilities. While prior works demonstrate that UED has the potential to learn a robust policy, their performance is constrained by the capabilities of the environment generation. To this end, we propose a novel UED algorithm, adversarial environment design via regret-guided diffusion models (ADD). The proposed method guides the diffusion-based environment generator with the regret of the agent to produce environments that the agent finds challenging but conducive to further improvement. By exploiting the representation power of diffusion models, ADD can directly generate adversarial environments while maintaining the diversity of training environments, enabling the agent to effectively learn a robust policy. Our experimental results demonstrate that the proposed method successfully generates an instructive curriculum of environments, outperforming UED baselines in zero-shot generalization across novel, out-of-distribution environments. Project page: https://***/projects/ADD © 2024, CC BY-NC-SA.

关键词： Adversarial machine learning

NMPC Strategy for Safe Robot Navigation in Unknown Environments Using Polynomial Zonotopes

学校读者我要写书评

暂无评论

NMPC Strategy for Safe Robot Navigation in Unknown Environme...

IEEE Conference on Decision and Control

作者： Iuro B. P. Nascimento Brenner S. Rego Luciano C. A. Pimenta Guilherme V. Raffo Graduate Program in Electrical engineering Federal University of Minas Gerais Brazil Department of Electrical and Computer Engineering University of São Paulo Brazil Department of Electronic Engineering Federal University of Minas Gerais Brazil

This work proposes a nonlinear model predictive control (NMPC) strategy for robot navigation in cluttered unknown environments using polynomial zonotopes. The information provided by a laser sensor is used in the computation of the collision-free area. The procedure splits the area into convex subregions which are converted into polynomial zonotopes (PZs) to generate constraints for the NMPC optimal control problem. The PZ is a set representation that can describe polytopes using fewer constraints than conventional half-space representations, thus being more efficient while maintaining the accuracy equivalent to the polytopic case. Numerical experiments demonstrate the advantages of the proposed strategy.

关键词：

Disentangled Motion Modeling for Video Frame Interpolation 39

学校读者我要写书评

暂无评论

Disentangled Motion Modeling for Video Frame Interpolation

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Lew, Jaihyun Choi, Jooyoung Shin, Chaehun Jung, Dahuin Yoon, Sungroh Interdisciplinary Program in AI Seoul National University Korea Republic of Department of Electrical and Computer Engineering Seoul National University Korea Republic of School of Computer Science and Engineering Soongsil University Korea Republic of AIIS ASRI and INMC Seoul National University Korea Republic of

ISBN: (纸本)157735897X

Video Frame Interpolation (VFI) aims to synthesize intermediate frames between existing frames to enhance visual smoothness and quality. Beyond the conventional methods based on the reconstruction loss, recent works have employed generative models for improved perceptual quality. However, they require complex training and large computational costs for pixel space modeling. In this paper, we introduce disentangled Motion Modeling (MoMo), a diffusion-based approach for VFI that enhances visual quality by focusing on intermediate motion modeling. We propose a disentangled two-stage training process. In the initial stage, frame synthesis and flow models are trained to generate accurate frames and flows optimal for synthesis. In the subsequent stage, we introduce a motion diffusion model, which incorporates our novel U-Net architecture specifically designed for optical flow, to generate bi-directional flows between frames. By learning the simpler low-frequency representation of motions, MoMo achieves superior perceptual quality with reduced computational demands compared to the generative modeling methods on the pixel space. MoMo surpasses state-of-the-art methods in perceptual metrics across various benchmarks, demonstrating its efficacy and efficiency in VFI. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Interpolation

Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lee, Saehyung Yoon, Seunghyun Bui, Trung Shi, Jing Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Adobe Research Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

Multimodal large language models (MLLMs) excel at generating highly detailed captions but often produce hallucinations. Our analysis reveals that existing hallucination detection methods struggle with detailed captions. We attribute this to the increasing reliance of MLLMs on their generated text, rather than the input image, as the sequence length grows. To address this issue, we propose a multiagent approach that leverages LLM-MLLM collaboration to correct given captions. Additionally, we introduce an evaluation framework and a benchmark dataset to facilitate the systematic analysis of detailed captions. Our experiments demonstrate that our proposed evaluation method better aligns with human judgments of factuality than existing metrics and that existing approaches to improve the MLLM factuality may fall short in hyper-detailed image captioning tasks. In contrast, our proposed method significantly enhances the factual accuracy of captions, even improving those generated by GPT-4V. Finally, we highlight a limitation of VQA-centric benchmarking by demonstrating that an MLLM’s performance on VQA benchmarks may not correlate with its ability to generate detailed image captions. © 2024, CC BY.

关键词： Image enhancement

Towards cross-modal causal structure and representation learning 2

学校读者我要写书评

暂无评论

Towards cross-modal causal structure and representation lear...

2nd Machine Learning for Health Symposium, ML4H 2022

作者： Mao, Haiyi Liu, Hongfu Xiaotian Dou, Jason Benos, Panayiotis V. Joint CMU-Pitt PhD Program in Computational Biology University of Pittsburgh United States Michtom School of Computer Science Brandeis University United States Department of Electrical and Computer Engineering University of Pittsburgh United States Department of Epidemiology University of Florida United States

Does the SARS-CoV-2 virus cause patients' chest X-Rays ground-glass opacities? Does an IDH-mutation cause differences in patients' MRI images? Conventional causal discovery algorithms, although well developed to uncover the cause-effect relationships on structured data, cannot elucidate causal relations between unstructured images and structured scalar variables due to the complexity of the former. In this paper, we consider causal discovery between images and structured (scalar) variables. Specifically, we derive low dimensional image representations to analyze with structured variables. We propose a two-module amortized variational algorithm named Cross-Modal Variational Causal representation and structure Learning (CMCL). CMCL jointly learns identifiable representations given a set of independent structured variables and causal relations via formulating latent representations and structured variables into a direct acyclic graph. Moreover, we further enforce counterfactual invariance/variance onto representations. We demonstrate that CMCL outperforms other related methods on synthetic datasets and validate causal relations on semi-synthetic datasets by visualization. © 2022 P.N. Argaw, E. Healey & I.S. Kohane.

关键词： Coronavirus

Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards

学校读者我要写书评

暂无评论

Safe CoR: A Dual-Expert Approach to Integrating Imitation Le...

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Hyeokjin Kwon Gunmin Lee Junseo Lee Songhwai Oh Interdisciplinary Program in Artificial Intelligence and ASRI Seoul National University Seoul Korea Department of Electrical and Computer Engineering and ASRI Seoul National University Seoul Korea

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In the realm of autonomous agents, ensuring safety and reliability in complex and dynamic environments remains a paramount challenge. Safe reinforcement learning addresses these concerns by introducing safety constraints, but still faces challenges in navigating intricate environments such as complex driving situations. To overcome these challenges, we present the safe constraint reward (Safe CoR) framework, a novel method that utilizes two types of expert demonstrations—reward expert demonstrations focusing on performance optimization and safe expert demonstrations prioritizing safety. By exploiting a constraint reward (CoR), our framework guides the agent to balance performance goals of reward sum with safety constraints. We test the proposed framework in diverse environments, including the safety gym, metadrive, and the real-world Jackal platform. Our proposed framework improves algorithm performance by 39% and reduces constraint violations by 88% on the real-world Jackal platform, highlighting its effectiveness. Through this innovative approach, we expect significant advancements in real-world performance, leading to transformative effects in the realm of safe and reliable autonomous agents.

关键词： Navigation Imitation learning Focusing Reinforcement learning Autonomous agents Safety Reliability Optimization Intelligent robots Faces

ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose Estimation and Motion Inbetweening

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jang, Hojun Kim, Young Min Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University Korea Republic of

We present Reusable Motion prior (ReMP), an effective motion prior that can accurately track the temporal evolution of motion in various downstream tasks. Inspired by the success of foundation models, we argue that a robust spatio-temporal motion prior can encapsulate underlying 3D dynamics applicable to various sensor modalities. We learn the rich motion prior from a sequence of complete parametric models of posed human body shape. Our prior can easily estimate poses in missing frames or noisy measurements despite significant occlusion by employing a temporal attention mechanism. More interestingly, our prior can guide the system with incomplete and challenging input measurements to quickly extract critical information to estimate the sequence of poses, significantly improving the training efficiency for mesh sequence recovery. ReMP consistently outperforms the baseline method on diverse and practical 3D motion data, including depth point clouds, LiDAR scans, and IMU sensor data. Project page is available in https://***/ReMP. Copyright © 2024, The Authors. All rights reserved.

关键词： Reusability

RN-SDEs: Limited-Angle CT Reconstruction with Residual Null-Space Diffusion Stochastic Differential Equations

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guo, Jiaqi Lopez-Tapia, Santiago Li, Wing Shun Wu, Yunnan Carignano, Marcelo Backman, Vadim Dravid, Vinayak P. Katsaggelos, Aggelos K. The Department of Electrical and Computer Engineering Northwestern University IL60201 United States The Applied Physics Program Northwestern University EvanstonIL60201 United States

Computed tomography is a widely used imaging modality with applications ranging from medical imaging to material analysis. One major challenge arises from the lack of scanning information at certain angles, leading to distorted CT images with artifacts. This results in an ill-posed problem known as the Limited Angle Computed Tomography (LACT) reconstruction problem. To address this problem, we propose Residual Null-Space Diffusion Stochastic Differential Equations (RN-SDEs), which are a variant of diffusion models that characterize the diffusion process with mean-reverting (MR) stochastic differential equations. To demonstrate the generalizability of RN-SDEs, our experiments are conducted on two different LACT datasets, i.e., ChromSTEM and C4KC-KiTS. Through extensive experiments, we show that by leveraging learned Mean-Reverting SDEs as a prior and emphasizing data consistency using Range-Null Space Decomposition (RNSD) based rectification, RN-SDEs can restore high-quality images from severe degradation and achieve state-of-the-art performance in most LACT tasks. Additionally, we present a quantitative comparison of computational complexity and runtime efficiency, highlighting the superior effectiveness of our proposed approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems