98%
921
2 minutes
20
Accurate road surface monitoring is essential for ensuring vehicle and pedestrian safety, and it relies on robust data acquisition and analysis methods. This study examines the classification of road surface conditions using single- and multi-head deep learning architectures, specifically Convolutional Neural Networks (CNNs) and CNNs combined with Long Short-Term Memory (LSTM) layers, applied to data from Inertial Measurement Units (IMUs) mounted on vehicle's sprung and unsprung masses. Various model architectures were tested, incorporating IMU data from different positions and utilizing both acceleration and angular velocity features. A grid search was conducted to fine-tune the architectures' hyperparameters, including the number of filters, kernel sizes, and LSTM units. Results show that CNN+LSTM models generally outperformed CNN-only models. The highest-performing model, which used data from three IMUs in a single-head architecture, achieved a macro F1-score of 0.9338. The study highlights the effectiveness of combining IMU data in a single-head architecture and suggests that further improvements in classification accuracy can be achieved by refining the architectures and enhancing the dataset, particularly for more challenging road surface classes.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12241564 | PMC |
http://dx.doi.org/10.1038/s41598-025-10573-2 | DOI Listing |
Nanoscale
September 2025
School of Materials and Energy, University of Electronic Science and Technology of China, Chengdu 611731, China.
Although improving the charging cutoff voltage is an effective strategy to increase its capacity, LiCoO ("LCO") undergoes rapid capacity decay due to severe structural and interface degradations at high voltages. Herein, we proposed a multifunctional surface modification by coating nano-sized entropy materials (Li-La-Ti-Zr-Co-O, Nano-MEO). Nano-MEO rivets were constructed on the surface of LCO, which stabilized the fragile surface.
View Article and Find Full Text PDFFood Chem X
August 2025
School of Life Science, Anqing Normal University, Jixian North Road1318, Yixiu District, Anqing 246052, Anhui Province, China.
Frozen storage deteriorates the texture and digestibility of frozen rice dough by damaging gliadin structure and starch integrity. This study investigated carboxymethyl chitosan (CMCh) and sodium carboxymethyl cellulose (CMCNa) as cry-oprotectants to mitigate these effects. Comprehensive analysis utilizing nuclear magnetic resonance (NMR), texture profile analysis (TPA), dynamic contact angle measurement (DCAT21), reversed-phase high-performance liquid chromatography (RP-HPLC), and circular dichroism (CD) demonstrated that 1.
View Article and Find Full Text PDFFood Prot Trends
June 2025
Dept. of Food, Nutrition, and Packaging Sciences, 220 Poole Agriculture Center, Clemson University, Clemson, SC 29634, USA.
Surface sanitation is used to mitigate the transmission of infectious agents and is the collective process of washing a surface then rinsing it with potable water to remove debris and residual cleaning agent. If necessary and depending on surface type, contamination event, or regulatory requirement, an antimicrobial agent (chemical sanitizer or disinfectant) registered with the Environmental Protection Agency or heat (steam or hot water) can be applied to the surface to reduce or inactivate pathogenic microorganisms. The absence of universally defined terms and regulations pertaining to the various stages of surface sanitation has resulted in confusion, potentially leading to inadequate sanitation practices and persistent surface contamination.
View Article and Find Full Text PDFJ Phys Chem Lett
September 2025
Collaborative Innovation Center of Advanced Microstructures, National Laboratory of Solid State Microstructures, College of Engineering and Applied Sciences, Nanjing University, No. 22 Hankou Road, Nanjing, Jiangsu 210093, P. R. China.
The oxygen evolution reaction (OER) performance of commercial TiO-supported IrO (IrO/TiO) suffers from the high electron transfer barriers at the IrO/TiO interface. Herein, we develop a cathodic polarization strategy to protonate TiO (p-TiO) in a commercial IrO/TiO catalyst. The high-density Ti-OH polaronic states on the surface of protonated TiO greatly contribute to the decrease in the electron transfer barriers at the IrO/TiO interface.
View Article and Find Full Text PDFISA Trans
September 2025
School of Automation, Northwestern Polytechnical University,1 Dongxiang Road, Chang'an District, Xi'an, Shaanxi 710129, PR China. Electronic address:
A novel practical predefined-time sliding mode control strategy is proposed for the flight formation of a small tandem-rotor wheeled UAV (TRW-UAV) with unknown upper bound external disturbances and uncertainties in this paper. Firstly, a new predefined-time sliding mode surface is proposed to guide all errors of the position and velocity loops to converge to the origin in a predefined-time. Furthermore, a dynamic surface control approach is utilized to circumvent the higher-order differentiation when controlling the actuator loop.
View Article and Find Full Text PDF