<rss version="2.0" xmlns:atom="https://www.w3.org/2005/Atom">
  <channel>
    <title>Transport Research International Documentation (TRID)</title>
    <link>https://trid.trb.org/</link>
    <atom:link href="https://trid.trb.org/Record/RSS?s=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" rel="self" type="application/rss+xml" />
    <description></description>
    <language>en-us</language>
    <copyright>Copyright © 2026. National Academy of Sciences. All rights reserved.</copyright>
    <docs>http://blogs.law.harvard.edu/tech/rss</docs>
    <managingEditor>tris-trb@nas.edu (Bill McLeod)</managingEditor>
    <webMaster>tris-trb@nas.edu (Bill McLeod)</webMaster>
    <image>
      <title>Transport Research International Documentation (TRID)</title>
      <url>https://trid.trb.org/Images/PageHeader-wTitle.jpg</url>
      <link>https://trid.trb.org/</link>
    </image>
    <item>
      <title>Strong vibration signal reconstruction of long-span bridges based on distributed optical fiber acoustic sensing</title>
      <link>https://trid.trb.org/View/2685144</link>
      <description><![CDATA[The dynamic response monitoring of long-span bridges during strong vibrations is significant for bridge health monitoring. An effective method to measure the distributed vibration of a long-span bridge is the distributed optical fiber acoustic sensing (DAS) technique, which measures the optical phase and can acquire vibration signals of numerous sensing points. However, conventional demodulation results in severe signal distortion as the amplitude of strong vibrations exceeds the restriction of unwrapping algorithm. Hence, damage-sensitive parameters like mode shapes cannot be extracted. In this study, we propose a strong vibration signal reconstruction algorithm for DAS systems, which makes full use of bridge dynamics principles and the information from reference sensors. The algorithm extracts intrinsic mode functions from reference sensors and builds normalized modal coordinate functions to reconstruct optical phase signals based on the strain-to-phase transformation. Multi-parameter optimization is employed to determine the amplitudes and phases of each mode. A vibration experiment was conducted on a scaled model of a real sea-crossing cable-stayed bridge. The heavy hammer-induced vibration waveforms of 25 sensing points on the deck could be reconstructed with a 0.25 m measuring resolution. The maximum reconstructed strain in the experiment was 255.3 με. The first 6 bending strain mode shapes were extracted with an average consistent modal indicator of 87.15%. The average modal assurance criterion relative to fiber-Bragg-grating results was 0.9402, indicating significant consistency. This study contributes to the high-amplitude vibration measurement of long-span bridges, especially under severe loading conditions.]]></description>
      <pubDate>Thu, 09 Jul 2026 13:29:25 GMT</pubDate>
      <guid>https://trid.trb.org/View/2685144</guid>
    </item>
    <item>
      <title>A Real-Time Monitoring and Rapid Warning Method for Guardrail Collisions in Intelligent Transportation Systems</title>
      <link>https://trid.trb.org/View/2706218</link>
      <description><![CDATA[This article proposes a method for real-time monitoring and rapid alert for guardrail collisions based on Distributed Acoustic Sensing (DAS). The aim is to enhance traffic safety through continuous analysis of vibration signals. To achieve this, a system architecture that combines both hardware and software design has been developed, enabling the handling of the entire process from signal acquisition and decoding to intelligent event recognition and visualization. To improve signal reliability, an adaptive noise reduction algorithm and a multi-level feature extraction method are introduced, enabling accurate differentiation between collision events and environmental disturbances. Tests at various vehicle speeds show that the DAS-based system detects collisions with over 98% accuracy and cuts false alarms by more than 60% compared to traditional video and point-sensor monitoring. It can locate accidents with an average error of 4.2 meters and respond in under 1 second, demonstrating both its accuracy and speed. These results confirm the method’s effectiveness and reliability for enhancing transportation safety.]]></description>
      <pubDate>Mon, 22 Jun 2026 07:29:01 GMT</pubDate>
      <guid>https://trid.trb.org/View/2706218</guid>
    </item>
    <item>
      <title>Vehicle-induced bridge dynamic response monitoring and displacement estimation using distributed acoustic sensing</title>
      <link>https://trid.trb.org/View/2672197</link>
      <description><![CDATA[Many bridges in operation today are aging, highlighting the need for advanced structural health monitoring solutions to ensure continued safety and performance. In this study, we propose an integrated framework that leverages Distributed Acoustic Sensing (DAS) with self-deployed fibers to monitor vehicle-induced dynamic response of bridges and to convert DAS-observed strain rate data into displacement—allowing direct alignment with standard engineering evaluation metrics used in structural codes. Validation against Laser Doppler Vibrometer (LDV) measurements shows high accuracy of the DAS-estimated bridge displacements, with an Average Percentage Variation Error (APVE) below 4.98%. Additionally, vehicle speeds are estimated from DAS data to demonstrate the feasibility of real-time and anonymous traffic monitoring. The observed vehicle speed distribution closely aligns with the tiered penalty thresholds defined in traffic regulations, indicating that DAS holds strong potential for future traffic monitoring and management applications. This study offers a practical and innovative approach to dynamic bridge monitoring and displacement estimation using DAS technology.]]></description>
      <pubDate>Wed, 13 May 2026 09:33:31 GMT</pubDate>
      <guid>https://trid.trb.org/View/2672197</guid>
    </item>
    <item>
      <title>Quantum machine learning for passive sonar: Spectral feature extraction and Hybrid convolution neural network classification of ship propeller signals</title>
      <link>https://trid.trb.org/View/2697578</link>
      <description><![CDATA[Underwater acoustic classification of propeller-driven vessels is hindered by environmental variability, limited labeled data, and the operator-dependent nature of Detection of Envelope Modulation on Noise (DEMON) preprocessing. We present a two-stage framework consisting of (i) a Spectral Amplitude Variation (SAV) algorithm that extracts discriminative frequencies through temporal variance of spectral amplitudes without manual bandwidth selection, and (ii) a Hybrid Quantum-Convolutional Neural Network (HQ-CNN) that integrates a 10-qubit parameterized quantum circuit with classical convolutional layers. Mathematical analysis shows that SAV exhibits cubic noise-power dependence compared with DEMON quartic dependence, providing improved robustness in low-SNR regimes. On the ShipEar and DeepShip benchmarks, SAV achieves detection rates of 98.22% and 99.04%, respectively, with false-alarm rates of 3.5% and 3.2%, while operating from 140x to 175x faster than DEMON-Hilbert. The HQ-CNN attains classification accuracies of 93.7% (ShipEar) and 96.8% (DeepShip), outperforming a classical CNN baseline by 3.7 and 5.2 percentage points. Source-stratified 5-fold cross-validation with BCa bootstrap (B = 10,000) confirms statistical significance (p<0.05, d = 3.10 and 4.83). Systematic comparison against seven classical regularization techniques demonstrates that the HQ-CNN yields near-zero generalization gaps (0.2% and 0.15%). Analysis of the trained quantum circuit reveals that individual qubits specialize in distinct frequency bands consistent with established underwater acoustic source mechanisms. All quantum-circuit evaluations were performed via noiseless statevector simulation and therefore represent an upper bound on performance attainable with current NISQ hardware.]]></description>
      <pubDate>Thu, 30 Apr 2026 16:39:45 GMT</pubDate>
      <guid>https://trid.trb.org/View/2697578</guid>
    </item>
    <item>
      <title>Advancing underwater acoustic target recognition in low-SNR environments with UATR-DIFF-transformer</title>
      <link>https://trid.trb.org/View/2631586</link>
      <description><![CDATA[Underwater Acoustic Target Recognition (UATR) using radiated noise holds significant potential for marine monitoring. However, existing deep learning approaches often struggle to effectively capture the essential spectral-temporal features in complex underwater signals, especially under low signal-to-noise ratio (SNR) conditions. To address this challenge, we present UATR-DIFF-Transformer, which integrates a differential attention mechanism and polynomial loss optimization. The proposed model captures dynamic variations of features across spatial and frequency dimensions through a differential attention module, enhancing the focus on critical features, while polynomial loss function optimization ensures clearer inter-class boundary delineation. Experimental evaluations on the Shipsear and DeepShip datasets demonstrate that this approach substantially improves classification accuracy compared to conventional Transformer models, achieving 90.26 % (+2.59 %) on Shipsear and 97.84 % (+1.72 %) on DeepShip. Moreover, the model demonstrates strong robustness to SNR fluctuations: at -10 dB, it outperforms the Transformer by 25.31 % on Shipsear and 14.41 % on DeepShip, effectively mitigating performance degradation. In addition, it enhances computational efficiency without compromising accuracy, reducing parameters by 49.7 % and FLOPs by 69.0 % compared to the standard Transformer, highlighting its practical value. These findings provide new ideas for the development of efficient and robust underwater monitoring system, and promote the development of marine environment sensing technology. This framework collectively advances underwater acoustic recognition capabilities by synergistically addressing feature representation learning and decision boundary optimization in challenging low-SNR scenarios.]]></description>
      <pubDate>Mon, 27 Apr 2026 15:01:22 GMT</pubDate>
      <guid>https://trid.trb.org/View/2631586</guid>
    </item>
    <item>
      <title>High-frequency acoustic coherent reflection from sea ice ridges: effect of ice characteristics and geometry</title>
      <link>https://trid.trb.org/View/2638249</link>
      <description><![CDATA[Environmental changes in the Arctic have increased the proportion of first-year ice while reducing multiyear ice, altering ice properties. These changes may affect the performance of underwater acoustic systems used for communication, navigation and ocean monitoring systems in Arctic sea. This study investigates the effects of sea ice age and ridge geometry on high-frequency coherent reflection loss. We model acoustic scattering from rough sea ice using the Helmholtz–Kirchhoff integral. The local reflection coefficient is derived from a water–ice–air layered model, and the ridge is assumed to be longitudinally-invariant to reduce computational cost. Results show that the under-ice geometry (keel) significantly influences shadow zone formation and reflection loss, while the upper-ice structure (sail) has a limited effect. The shear wave speed of ice is a key property that determines the grazing angle range for minimal reflection loss, which is critical for long-range propagation. First-year ice, due to its lower shear wave speed, is expected to produce greater reflection loss at low grazing angles than multiyear ice. Time-domain analysis reveals that the keel, ice properties, and thickness lead to multiple signal arrivals. These findings support acoustic propagation modeling and the operation of underwater acoustic systems in the Arctic.]]></description>
      <pubDate>Mon, 27 Apr 2026 15:01:20 GMT</pubDate>
      <guid>https://trid.trb.org/View/2638249</guid>
    </item>
    <item>
      <title>Intelligent Vehicle Automatic Identification and Classification With Distributed Acoustic Sensing</title>
      <link>https://trid.trb.org/View/2610672</link>
      <description><![CDATA[Distributed Acoustic Sensing (DAS) is an emerging vibration collection technology with advantages such as low cost, high-density sampling, and high sensitivity. It utilizes regional unlit fiber-optic telecommunication infrastructure (dark fiber) in the urban underground to record real-time environmental signals. How to identify vehicle signals, classify vehicle types, and estimate vehicle speeds from DAS signals has significant potential for the development of intelligent urban transportation. Addressing the challenges of high-noise environments and dense traffic, we develop an end-to-end two-stage deep learning process to identify and classify various vehicle signals in urban traffic rapidly. First, we propose the CarDenoiseNet network, based on Generative Adversarial Networks (GAN) and contrastive learning, to denoise and enhance the weak signal of DAS data. Then, the YOLOv8 segmentation model is employed to segment and classify the vehicle signal. Finally, the vehicle speeds are estimated using the segmented vehicle trajectory time and location information. We use the urban DAS field data recorded in the downtown area of Changchun to test the proposed workflow. The test result has good generalization and over 90% accuracy in identifying different vehicle types and speeds in high-density traffic environments. Moreover, transfer learning successfully applies the model to other datasets, proving its excellent generalization ability. Additionally, statistical analysis of traffic flow and speed trends provides technical references for alleviating urban traffic congestion, reducing traffic accidents, and enhancing the intelligence level of urban traffic management.]]></description>
      <pubDate>Thu, 26 Mar 2026 17:02:26 GMT</pubDate>
      <guid>https://trid.trb.org/View/2610672</guid>
    </item>
    <item>
      <title>Precision Traffic Monitoring: Leveraging Distributed Acoustic Sensing and Deep Neural Networks</title>
      <link>https://trid.trb.org/View/2561835</link>
      <description><![CDATA[Distributed Acoustic Sensing (DAS) has recently emerged as a promising technology for traffic monitoring. It transforms standard fiber-optic telecommunication cables into an array of vibration sensors capable of capturing vehicle-induced subsurface deformation with high spatio-temporal resolution. In this study, we propose a deep learning framework for the detection and velocity estimation of traffic flow. Our neural network based model yields accurate and well-resolved vehicle localization and speed tracking, outperforming off-the-shelf Dynamic Time Warping based solutions while achieving an order of magnitude faster processing time. A multi-day comparison with dedicated sensors installed along an urban highway shows a strong correlation, even under dense traffic conditions.]]></description>
      <pubDate>Mon, 23 Mar 2026 17:14:34 GMT</pubDate>
      <guid>https://trid.trb.org/View/2561835</guid>
    </item>
    <item>
      <title>Quantifying water accumulation in parallel wire bridge cables or hangers using magnetostrictive guided waves</title>
      <link>https://trid.trb.org/View/2669595</link>
      <description><![CDATA[Water accumulation in bridge cables or hangers caused by sealing failures poses a significant threat to structural integrity due to corrosion. This study introduces a novel non-destructive method using magnetostrictive guided waves to quantify water accumulation in bridge cables or hangers to enhance structural health monitoring. By analyzing the reflection and transmission properties of elastic waves at solid-liquid interfaces, the method employs longitudinal wave modes to optimize detection parameters. Finite element simulations and laboratory experiments on a cable validate the approach, showing an exponential decay in guided wave echo amplitudes and a linear increase in attenuation coefficients with increasing water accumulation length. Field tests on a tied-arch bridge confirm the method’s efficacy with results verified. This approach offers significant improvements over invasive techniques which would provide a sensitive and efficient tool for monitoring the cable and hanger conditions.]]></description>
      <pubDate>Mon, 23 Mar 2026 15:25:40 GMT</pubDate>
      <guid>https://trid.trb.org/View/2669595</guid>
    </item>
    <item>
      <title>Identification of high-impact wheels on rail transit rolling stock through acoustic sensing and machine learning</title>
      <link>https://trid.trb.org/View/2643038</link>
      <description><![CDATA[This study investigates the potential for developing and leveraging machine learning algorithms to identify problematic train wheels that generate high impact loads using sound classification analysis. The data used in this research were collected from a heavy rail transit agency in the US. Both the wheel-rail interface load magnitude and sound pressure levels were collected and processed. Each audio sample was transformed into a spectrogram, which provided a visual representation of the sound signal. To classify spectrograms into two distinct categories representative of high impact loads and normal wheel loads, a convolutional neural network (CNN) was developed and trained on the spectrograms as input, which were labeled based on their loading conditions. The performance of the trained model – 72% accuracy – was satisfactory given constraints present and proves the feasibility to predict railway wheel loading condition based on the sound generated during train passage. This potential alternative method to the current complex system of track-mounted strain gauges for monitoring wheel health could yield substantial benefits to rail operators with limited resources or that require unintrusive or portable wheel condition monitoring.]]></description>
      <pubDate>Wed, 18 Mar 2026 09:01:39 GMT</pubDate>
      <guid>https://trid.trb.org/View/2643038</guid>
    </item>
    <item>
      <title>Inspection, Evaluation, and Monitoring of Suspension Bridge Cables</title>
      <link>https://trid.trb.org/View/2235233</link>
      <description><![CDATA[The assessment of the condition of the main cables of suspension bridges requires specialized techniques that have been developed over the last few decades. In the United States, the Federal Highways Administration (FHWA) has introduced guidelines for visual inspection of fracture-critical bridge members, including suspension bridge cables. Recently, the National Cooperative Highway Research Program (NCHRP) has published more detailed guidelines focused on the inspection and evaluation of parallel wire suspension cables. Also, over the past ten years, new acoustic monitoring technologies have been introduced that permit long-term monitoring of cables to detect breaking wires.]]></description>
      <pubDate>Tue, 24 Feb 2026 09:00:44 GMT</pubDate>
      <guid>https://trid.trb.org/View/2235233</guid>
    </item>
    <item>
      <title>A Deep Learning Image Segmentation Model for Detection of Weak Vehicle-Generated Quasi-Static Strain in Distributed Acoustic Sensing</title>
      <link>https://trid.trb.org/View/2561798</link>
      <description><![CDATA[Distributed Acoustic Sensing (DAS) instrument connected to dark fibers that widely deployed near roads can collect quasi-static strain signals generated by vehicles over a large range. This approach addresses the high deployment and maintenance costs and limited coverage of traditional roadside sensing technologies, making DAS a highly promising vehicle detection technology for intelligent transportation systems. However, using existing communication cables rather than specially laid sensing cables as the DAS sensing medium, while offering ultra-low deployment and maintenance cost advantages, poses significant challenges for detecting lightweight, low-speed vehicles that are far from the fiber cable. The quasi-static strain generated by such vehicles are low and easily overwhelmed by environmental noise and DAS fading noise. In this paper, we analyze the causes of weak vehicle quasi-static signals and propose a Unet image segmentation network, trained to recognize these weak signals using a large window with a small step size for data input. In a typical campus test scenario containing numerous lightweight low-speed vehicles, we tested various vehicle quasi-static signals using Unet. The results demonstrated that our method has high recognition accuracy and excellent resistance to DAS fading noise.]]></description>
      <pubDate>Tue, 24 Feb 2026 09:00:44 GMT</pubDate>
      <guid>https://trid.trb.org/View/2561798</guid>
    </item>
    <item>
      <title>An Autonomous Underwater Vehicle-Assisted Adaptive Trust Prediction Model for UASNs</title>
      <link>https://trid.trb.org/View/2591939</link>
      <description><![CDATA[Underwateracoustic sensor networks (UASNs) provide significant support for marine intelligent transportation system. As an effective security mechanism, the trust prediction model has been gradually deployed in UASNs to detect anomalous attacks and guarantee the security of marine transportation. However, in existing research on trust models for UASNs, the impact of multidimensional trust features on the trust prediction process is usually treated as the same, even in dynamic current environments and dynamic network topologies. In addition, underwater sensor nodes undertake excessive trust computation in the traditional UASN architecture. In this paper, we introduce the Autonomous Underwater Vehicle (AUV) as the edge device to construct the edge-enabled UASN architecture, and propose an AUV-assisted adaptive Trust Prediction model, which we name ATP. Furthermore, by analyzing the characteristics of the edge-enabled UASN architecture, we extract trust features from AUV and underwater sensor nodes respectively, and AUV is utilized for trust computation and prediction. In order to improve the performance of anomalous node detection, we adaptively adjust the contribution of different trust features to trust prediction based on the attention mechanism. Evaluation results indicate that our proposed ATP model is able to detect anomalous nodes effectively, and it achieves higher accuracy than that of the two established trust models.]]></description>
      <pubDate>Thu, 13 Nov 2025 16:59:49 GMT</pubDate>
      <guid>https://trid.trb.org/View/2591939</guid>
    </item>
    <item>
      <title>Exploring Distributed Acoustic Sensing for Pedestrian Monitoring: Signal Characteristics and Identification</title>
      <link>https://trid.trb.org/View/2622039</link>
      <description><![CDATA[Distributed acoustic sensing (DAS) has shown potential for traffic monitoring: when applied to fiber optic cables installed near roadways, it can capture vibrations from roadway activities, including higher-frequency surface waves from the dynamic interaction between vehicles and the road surface, and low-frequency pseudo-static signals from ground deformation because of loading and unloading near the fiber. While prior studies have largely focused on vehicle monitoring using telecommunication cables offset from roadways, this study explores the use of DAS for pedestrian monitoring, which introduces new challenges because of lower amplitude and variability in movement patterns. The primary experimental site featured fiber optic cables embedded in the roadway, providing strong fiber–road coupling and high-sensitivity, high-resolution capture of pedestrian activity. Controlled experiments were conducted to simulate walking, jogging, running, and jumping. Signal characteristics were examined in relation to movement type, speed, the individual pedestrian, the DAS gauge length, and variations in data processing, such as decimation, filtering, initial roadway strain, and min-max scaling. Random forest (RF) and K-nearest neighbor (KNN) algorithms were used to identify pedestrian ID from the jump data, demonstrating the ability to capture subtle differences in movement. To complement these controlled experiments and address real-world variability, additional pedestrian signals were explored from a secondary site where fiber was buried along a water pipeline beneath an active road in a residential area. Despite increased noise and reduced coupling, pedestrian signals remained detectable, providing additional evidence for DAS sensitivity to pedestrian movements. These findings support the broader applicability of DAS for pedestrian-aware urban traffic monitoring.]]></description>
      <pubDate>Thu, 13 Nov 2025 16:57:43 GMT</pubDate>
      <guid>https://trid.trb.org/View/2622039</guid>
    </item>
    <item>
      <title>Rail track support condition monitoring with distributed acoustic sensing (DAS) system</title>
      <link>https://trid.trb.org/View/2577199</link>
      <description><![CDATA[Regular track support condition monitoring is critical for ensuring safe train operations and optimum scheduling of track maintenance activities. Unfortunately, most conventional monitoring systems cannot support continuous monitoring over long-track sections. Distributed Optical Fiber Sensing (DOFS) has recently been proposed as a viable alternative to accomplish this as it can measure mechanical and thermal strains over long distances. DOFS cables have been traditionally buried in the ground adjacent to the track. However, mounting the cable directly on the rail can give better information on wheel and rail defects and track support conditions. This paper presents findings from an ongoing research study aimed at investigating the feasibility of a type of DOFS called Distributed Acoustic Sensing (DAS) system for track support condition monitoring. Field testing was carried out, where a 50-m long track section was monitored using a DAS system. Two types of optical fiber cables were mounted to the rail using two different approaches. The instrumented track segment was loaded using a locomotive moving at speeds ranging from 16 km/h to 97 km/h. Varying track support conditions were simulated through strategic removal of selected crossties. Test results showed that the DAS system could capture variations in the rail strain caused by changes in support conditions under loading at different speeds. This study marks the first successful application of a DAS system for track support condition monitoring through direct mounting on the rail.]]></description>
      <pubDate>Mon, 08 Sep 2025 14:54:44 GMT</pubDate>
      <guid>https://trid.trb.org/View/2577199</guid>
    </item>
  </channel>
</rss>