检索结果-内蒙古大学图书馆

Enhanced Prognostics and Health Management in Automated Driving Systems: Using Graph Neural Networks to Recognize Operational Contexts

学校读者我要写书评

暂无评论

Enhanced Prognostics and Health Management in Automated Driv...

Prognostics and System Health Management Conference (PHM)

作者： Peng Su Yeqi Wang Conglei Xiang Erik Wendel Madhav Mishra DeJiu Chen Department of Engineering Design Mechatronics Division KTH Royal Institute of Technology Stockholm Sweden Embedded Systems Master Program of Electrical Engineering and Computer Science (EECS) School KTH Royal Institute of Technology Stockholm Sweden Digital Systems Division RISE Research Institutes of Sweden Gothenburg Sweden

ISBN: (数字)9798350360585

ISBN: (纸本)9798350360592

Prognostics and health management (PHM) is an engineering discipline that aims to maintain system behaviour and function and ensure mission success, safety and effectiveness. Addressing the challenges in prognostics and health management for modern intelligent systems, especially automated driving systems, is complex due to the contextual nature of faults. This complexity necessitates a thorough understanding of spatial, and temporal conditions, and relationships within operational scenarios and life-cycle stages. This paper introduces a framework designed to automatically recognize driving scenarios in automated driving systems using graph neural networks (GNNs). The framework extracts relational data from image frames, constructing graph-based models and transforming unstructured sensory data into structured data with diverse node types and relationships. A specific graph neural network processes the graph model to reveal and detect operational conditions and relationships. The proposed framework is evaluated using the KITTI dataset, demonstrating superior performance compared to conventional feed-forward networks such as MLP, particularly in handling relational data.

关键词： Graph neural networks Data models Safety Complexity theory Data mining Prognostics and health management Intelligent systems

Dynamics of COVID-19 Misinformation: An Analysis of Conspiracy Theories, Fake Remedies, and False Reports

学校读者我要写书评

暂无评论

Dynamics of COVID-19 Misinformation: An Analysis of Conspira...

17th International Conference on Social Computing and Social Media, SCSM 2025, held as part of the 27th HCI International Conference, HCII 2025

作者： Thakur, Nirmalya Shao, Mingchen Knieling, Victoria Su, Vanessa Bian, Andrew Jeong, Hongseok Department of Electrical Engineering and Computer Science South Dakota School of Mines and Technology Rapid CitySD57701 United States Department of Computer Science Emory University AtlantaGA30322 United States Program in Linguistics Emory University AtlantaGA30322 United States Goizueta Business School Emory University AtlantaGA30322 United States

ISBN: (纸本)9783031935350

This paper makes four scientific contributions to the area of misinformation detection and analysis on digital platforms, with a specific focus on investigating how conspiracy theories, fake remedies, and false reports emerge, propagate, and shape public perceptions in the context of COVID-19. A dataset of 5,614 posts on the internet that contained misinformation about COVID-19 was used for this study. These posts were published in 2020 on 427 online sources (such as social media platforms, news channels, and online blogs) from 193 countries and in 49 languages. First, this paper presents a structured, three-tier analytical framework that investigates how multiple motives - including fear, politics, and profit - can lead to a misleading claim. Second, it emphasizes the importance of narrative structures, systematically identifying and quantifying the thematic elements that drive conspiracy theories, fake remedies, and false reports. Third, it presents a comprehensive analysis of different sources of misinformation, highlighting the varied roles played by individuals, state-based organizations, media outlets, and other sources. Finally, it discusses multiple potential implications of these findings for public policy and health communication, illustrating how insights gained from motive, narrative, and source analyses can guide more targeted interventions in the context of misinformation detection on digital platforms. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Data mining

Gene Name Recognition in Gene Pathway Figures Using Siamese Networks

学校读者我要写书评

暂无评论

Gene Name Recognition in Gene Pathway Figures Using Siamese ...

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Micheal Olaolu Arowolo Muhammad Azam Fei He Mihail Popescu Dong Xu Department of Public Health Sciences Health Informatics Program Xavier University of Louisiana New Orleans Louisiana USA Department of Electrical Engineering and Computer Science Bond Life Sciences Center University of Missouri Columbia Missouri USA Department of Health Management and Informatics University of Missouri Columbia Missouri USA

ISBN: (数字)9798350377613

ISBN: (纸本)9798350377620

The number of scientific papers related to biology is rapidly increasing, and with it, the number of pathway figures containing crucial biological information. However, manually annotating these figures is a time-consuming process, and current optical character recognition (OCR) methods are not effective in identifying gene names within these figures. To improve gene name recognition from pathway figures, we utilized a Siamese network that maps image segments to a library of pictures containing known gene name, like object recognition in many photo applications. We combined the triplet convolution neural network and the spatial pyramid pooling (TSPP-Net) to create a CNN triple loss function. We trained and tested the developed TSPP-Net network using 563 gene images from 45 pathway pictures, 1000 images of alphanumeric characters and gene names from HUGO and KEGG. To benchmark against major available OCR technologies, we used 20 randomly selected curated pathway genes. Additionally, we compared several models, such as VGG19, VGG16, Resnet-50 Resnet-18, Densnet-121, and Xception for the Siamese backbone network model. VGG16 achieved the best performance with an accuracy of 93%, which is much higher than the results obtained using OCR. Our code is publicly available at https://***/MuhammadAzam636/Siamese-Network.

关键词： Image recognition Accuracy Sensitivity Text recognition Biological system modeling Optical character recognition Neural networks Libraries Object recognition Biological information theory

Optical spectroscopy of excitons in ReS2 monolayers grown by chemical vapor deposition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ojo, Solomon Onasanya, Juwon Benamara, Morad Hamad, Bothina Manasreh, M.O. Material Science and Engineering program University of Arkansas FayettevilleAR72701 United States Institute of nanotechnology University of Arkansas FayettevilleAR72701 United States Physics Department University of Arkansas FayettevilleAR72701 United States Department of Electrical Engineering and Computer Science University of Arkansas FayettevilleAR72701 United States

Monolayers of ReS2 were grown by a chemical vapor deposition technique on SiO2/Si substrates and investigated at room temperature by using μ-Raman, μ-photoluminescence (PL) and absorbance spectroscopies. The Raman scattering spectrum exhibits several phonon modes that were confirmed by the computation analysis based on the density functional theory. The ReS2 structural integrity was confirmed by using the XRD and the energy dispersion spectroscopy that was obtained by the scanning electron microscopy. Photoluminescence spectra show excitons related to interband transition in thin monolayer flakes and bulk-like structures. Additionally, a sharp PL line located at 1.2620 eV with a second harmonic peak at 2.5420 eV were observed and explained in terms of interband excitonic transitions originated within the rhenium 5d orbit. An optical absorbance spectrum with an exciton peak around 1.4660 eV was obtained for an assembly of ReS2 flakes grown on silica substrate. Copyright © 2024, The Authors. All rights reserved.

关键词： Scanning electron microscopy

Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kim, Eunji Kim, Siwon Park, Minjun Entezari, Rahim Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Stability AI United Kingdom AIIS ASRI INMC ISRC Seoul National University Korea Republic of

Recent advancements in text-to-image models, such as Stable Diffusion, show significant demographic biases. Existing debiasing techniques rely heavily on additional training, which imposes high computational costs and risks of compromising core image generation functionality. This hinders them from being widely adopted to real-world applications. In this paper, we explore Stable Diffusion’s overlooked potential to reduce bias without requiring additional training. Through our analysis, we uncover that initial noises associated with minority attributes form "minority regions" rather than scattered. We view these "minority regions" as opportunities in SD to reduce bias. To unlock the potential, we propose a novel de-biasing method called ‘weak guidance,’ carefully designed to guide a random noise to the minority regions without compromising semantic integrity. Through analysis and experiments on various versions of SD, we demonstrate that our proposed approach effectively reduces bias without additional training, achieving both efficiency and preservation of core image generation functionality. © 2024, CC BY-NC-SA.

关键词： Digital elevation model

Dynamics of COVID-19 Misinformation: An Analysis of Conspiracy Theories, Fake Remedies, and False Reports

学校读者我要写书评

暂无评论

arXiv 2025年

关键词：

Downstream Task Performance of Pre-Trained Model For Outdoor Audio Event Classification

学校读者我要写书评

暂无评论

Downstream Task Performance of Pre-Trained Model For Outdoor...

International Conference of Signal Processing and Intelligent Systems (ICSPIS)

作者： Theresia Herlina Rochadiani Yaya Heryadi Ilvico Sonata Lukas Wawan Suparta BINUS Graduate Program- Computer Science Bina Nusantara University Jakarta Indonesia Cognitive Engineering Research Group Universitas Katolik Indonesia Atma Jaya Jakarta Indonesia Department of Electrical Engineering Institut Teknologi Nasional Yogyakarta Yogyakarta Indonesia

Our surroundings’ auditory landscapes are a wealth of knowledge, providing insights into a range of outdoor pursuits. The automatic classification of these actions using audio event detection and classification (AEDC) systems has a great deal of potential applications in environmental monitoring, security, surveillance, and driverless cars. Even though AEDC has advanced significantly in indoor settings, difficulties still exist outside because of the variable and changing acoustic conditions brought on by elements like the weather, different sound sources, and ambient noise from traffic and industry. This study suggests an outdoor audio event categorization model based on convolutional neural networks (CNNs). The suggested model shows passable accuracy by utilizing adaptation to the downstream task using the ESC-50 dataset and transfer learning from a pre-trained model. The effectiveness of multi-class audio classification models in downstream tasks is analyzed in this paper, with an emphasis on the effect of an increasing number of output classes on accuracy. Three models—three, four, and five classes—with different output class configurations are used in the study, and their training and validation accuracies are assessed. Although the accuracy scores above 80% are commendable, the data show a discernible reduction in performance as the number of classes rises. Notably, the three-class model attains a validation accuracy exceeding 90%, whereas the four-class and five-class models exhibit reduced accuracies, falling below 90% and 85%, respectively.

关键词：

From Lab to Field: Real-World Evaluation of an AI-Driven Smart Video Solution to Enhance Community Safety

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yao, Shanle Ardabili, Babak Rahimi Pazho, Armin Danesh Noghre, Ghazal Alinezhad Neff, Christopher Bourque, Lauren Tabkhi, Hamed Department of Electrical and Computer Engineering University of North Carolina at Charlotte United States Public Policy Program University of North Carolina at Charlotte 9201 University City Blvd CharlotteNC28223 United States

This article adopts and evaluates an AI-enabled Smart Video Solution (SVS) designed to enhance safety in the real world. The system integrates with existing infrastructure camera networks, leveraging recent advancements in AI for easy adoption. Prioritizing privacy and ethical standards, pose based data is used for downstream AI tasks such as anomaly detection. Cloud-based infrastructure and mobile app are deployed, enabling real-time alerts within communities. The SVS employs innovative data representation and visualization techniques, such as the Occupancy Indicator, Statistical Anomaly Detection, Bird’s Eye View, and Heatmaps, to understand pedestrian behaviors and enhance public safety. Evaluation of the SVS demonstrates its capacity to convert complex computer vision outputs into actionable insights for stakeholders, community partners, law enforcement, urban planners, and social scientists. This article presents a comprehensive real-world deployment and evaluation of the SVS, implemented in a community college environment across 16 cameras. The system integrates AI-driven visual processing, supported by statistical analysis, database management, cloud communication, and user notifications. Additionally, the article evaluates the end-to-end latency from the moment an AI algorithm detects anomalous behavior in real-time at the camera level to the time stakeholders receive a notification. The results demonstrate the system’s robustness, effectively managing 16 CCTV cameras with a consistent throughput of 16.5 frames per second (FPS) over a 21-hour period and an average end-to-end latency of 26.76 seconds between anomaly detection and alert issuance. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

Spectral Extremal Connectivity of Two-State Seizure Brain Waves

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Talento, Mara Sherlin D. Richards, Jordan Pinto-Orellana, Marco Huser, Raphael Ombao, Hernando C. Statistics Program Computer Electrical and Mathematical Science & Engineering Division King Abdullah University of Science and Technology 23955 - 6900 Saudi Arabia Neuro-AI Laboratory Computer Electrical and Mathematical Science & Engineering Division King Abdullah University of Science and Technology 23955 - 6900 Saudi Arabia School of Mathematics Maxwell Institute for Mathematical Sciences University of Edinburgh EdinburghEH9 3FD United Kingdom Department of Biomedical Engineering University of California Irvine92697 United States

Coherence analysis plays a vital role in the study of functional brain connectivity. However, coherence captures only linear spectral associations, and thus can produce misleading findings when ignoring variations of connectivity in the tails of the distribution. This limitation becomes important when investigating extreme neural events that are characterized by large signal amplitudes. The focus of this paper is to examine connectivity in the tails of the distribution, as this reveals salient information that may be overlooked by standard methods. We develop a novel notion of spectral tail association of periodograms to study connectivity in the network of electroencephalogram (EEG) signals of seizure-prone neonates. We further develop a novel non-stationary extremal dependence model for multivariate time series that captures differences in extremal dependence during different brain phases, namely burst-suppression and non-burst-suppression. One advantage of our proposed approach is its ability to identify tail connectivity at key frequency bands that could be associated with outbursts of energy which may lead to seizures. We discuss these novel scientific findings alongside a comparison of the extremal behavior of brain signals for epileptic and non-epileptic patients. © 2025, CC BY.

关键词： Electroencephalography