Results 81 to 90 of about 6,853 (246)

Anomalies-by-Synthesis: Anomaly Detection using Generative Diffusion Models for Off-Road Navigation

open access: yes2025 IEEE International Conference on Robotics and Automation (ICRA)
In order to navigate safely and reliably in off-road and unstructured environments, robots must detect anomalies that are out-of-distribution (OOD) with respect to the training data. We present an analysis-by-synthesis approach for pixel-wise anomaly detection without making any assumptions about the nature of OOD data.
Sunshine Jiang   +6 more
openaire   +2 more sources

Engineering of Crystal and Domain Structures in Epitaxial Y:HfO2 Thin Films by YSZ Substrate Miscut

open access: yesAdvanced Science, EarlyView.
We investigate how YSZ substrate miscut influences crystal structure and domain formation in epitaxial Y‐doped HfO2 thin films. Using magnetron sputtering, high‐resolution X‐ray diffraction, atomic‐resolution scanning transmission electron microscopy, and first‐principles calculations, we systematically examine the characteristics of thickness‐ and ...
Jun Young Lee   +12 more
wiley   +1 more source

Context-Aware Road Event Detection Using Hybrid CNN–BiLSTM Networks

open access: yesVehicles
Road anomaly detection is essential for intelligent transportation systems and road maintenance. This work presents a MATLAB-native hybrid Convolutional Neural Network–Bidirectional Long Short-Term Memory (CNN–BiLSTM) framework for context-aware road ...
Abiel Aguilar-González   +1 more
doaj   +1 more source

Diverse Landscape of Tunable Magnetic, Topological, and Ferroelectric States in 2D Ti3Se3Te2

open access: yesAdvanced Science, EarlyView.
Ti3Se3Te2 emerges as a multifunctional 2D van der Waals platform. The monolayer is a dynamically stable ferromagnetic quantum anomalous Hall insulator. In bilayers, two stacking configurations yield distinct phases: AA‐stacking hosts an altermagnetic quantum spin Hall insulator, while AA′‐stacking exhibits three‐state in‐plane ferroelectricity ...
Jiangtao Yu   +5 more
wiley   +1 more source

RAOD: A Benchmark for Road Abandoned Object Detection From Video Surveillance

open access: yesIEEE Access
Road abandoned objects are potential safety hazards in modern traffic transport, especially in highway scenes. Promptly detecting such obstacles on the road is of great significance for driving safety and Intelligent Transportation Systems (ITS). Current
Yajun Xu   +6 more
doaj   +1 more source

Interlayer‐Sliding‐Enabled Multiferroicity and Giant Switchable Anomalous Hall Conductivity in RuO2Zn2F2 Bilayer

open access: yesAdvanced Science, EarlyView.
Interlayer sliding in the RuO2Zn2F2 bilayer induces ferroelectricity and enables reversible valley polarization switching. The electric dipole and valley‐resolved band edges are intimately coupled, revealing sliding ferroelectricity as a powerful mechanism for electrical control of valley degrees of freedom in 2D materials.
Djamel Bezzerga   +3 more
wiley   +1 more source

Graph autoencoder with mirror temporal convolutional networks for traffic anomaly detection

open access: yesScientific Reports
Traffic time series anomaly detection has been intensively studied for years because of its potential applications in intelligent transportation. However, classical traffic anomaly detection methods often overlook the evolving dynamic associations ...
Zhiyu Ren   +6 more
doaj   +1 more source

Multidimensional and Multifunctional Laser‐Induced Graphene (LIG) for Point‐of‐Care and Wearable Biosensing, Theranostics, and Bioactive Interfaces Toward Personalized Healthcare and Regenerative Medicine

open access: yesAdvanced Science, EarlyView.
Multidimensional laser‐induced graphene (LIG) spanning from 0D to 3D architectures is comprehensively reviewed for multifunctional biomedical platforms, including biosensing, theranostics, and bioactive interface applications, which highlights its potentials for point‐of‐care diagnostics, wearable health monitoring, smart drug delivery, and tissue ...
Li Zhang   +3 more
wiley   +1 more source

Self‐Powered Bearing Sensing and Real‐Time Fault Diagnosis Enabled by Non‐Invasive Triboelectric Sensors and Edge AI Acceleration

open access: yesAdvanced Science, EarlyView.
This study achieves the synergistic integration of self‐powered sensing and edge AI acceleration to establish a real‐time fault diagnosis system. The proposed TENG‐based self‐powered bearing sensor (NSE‐TBS) and FPGA‐accelerated edge AI framework fundamentally break through the inherent limitations of conventional monitoring systems, including complex ...
Kehui Zhu   +7 more
wiley   +1 more source

Design of a Machine Learning Approach to Anomaly Detection in Tyre-Road Interaction

open access: yesIEEE Access
Tyres show a strong non-linear dependence on vertical force, road roughness, wear level, temperature gradient, and slip resulting in an additional challenge in calibration, whose parameters may vary significantly with the tyre’s condition.
Aleksandr Sakhnevych   +2 more
doaj   +1 more source

Home - About - Disclaimer - Privacy