<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>Development of driving condition classification based adaptive optimal control strategy for PHEV</title>
      <link>https://trid.trb.org/View/1641496</link>
      <description><![CDATA[In this study, driving condition classification and recognition based adaptive optimal control strategy is developed for new type four wheel drive plug-in hybrid electric vehicle (PHEV). First, power characteristics of the proposed PHEV are analysed. The basic rule based and adaptive optimal control strategies are developed. According to the support vector machine (SVM) based classification theory, the RBF neural network kernel function is introduced and the multi classification SVM with the one-against-one method is selected. The feature parameters are then determined and extracted using real road experiment data. It is seen from the classification results that RBF kernel function based SVM has relatively high accuracy of 93.2%. Based on the developed energy management strategy library and driving cost theory, adaptive optimal control strategy is developed using Matlab/Simulink. It is found from the simulation results that the adaptive optimal control achieves the efficiency increase of 13.4%, which implies validity of the proposed adaptive optimal control strategy.]]></description>
      <pubDate>Tue, 22 Oct 2019 14:42:38 GMT</pubDate>
      <guid>https://trid.trb.org/View/1641496</guid>
    </item>
    <item>
      <title>Model-based Sensor Fault Diagnosis of Vehicle Suspensions with a Support Vector Machine</title>
      <link>https://trid.trb.org/View/1645486</link>
      <description><![CDATA[In this paper, a means of generating residuals based on a quarter-car model and evaluating them using a support vector machine (SVM) is proposed. The proposed model-based residual generator shows very robust performance regardless of unknown road surface conditions. In addition, an SVM classifier without empirically set thresholds is used to evaluate the residuals. The proposed method is expected to reduce the effort required to design fault diagnosis algorithms. While an unknown input observer is used to generate the residual, the relative velocity of the vehicle suspension is obtained additionally. The proposed algorithm is verified using commercial vehicle simulator Carsim with Matlab & Simulink. As a result, the fault diagnosis algorithm proposed in this paper can detect sensor faults that cannot be detected by a limit checking method and can reduce the effort required when designing algorithms.]]></description>
      <pubDate>Tue, 22 Oct 2019 14:42:32 GMT</pubDate>
      <guid>https://trid.trb.org/View/1645486</guid>
    </item>
    <item>
      <title>ITS Support for Pedestrians and Bicyclists Count: Developing a Statewide Multimodal Count Program</title>
      <link>https://trid.trb.org/View/1649298</link>
      <description><![CDATA[It is critical to understand the travel behavior of pedestrians and cyclists on Louisiana’s roadways. Not only do pedestrian and cyclist counts assist in research for safety, but these statistics are also essential for planners and policymakers when evaluating the usage of roadways and dictating infrastructure spending. Better understanding of overall statewide and location-specific transportation trends ultimately affects long-term planning and investment. Counting of pedestrians and cyclists using video surveillance and image processing technology has promised to be effective and feasible. While the research on newer technologies is not as robust as that of traditional ones, there is enough evidence to justify and guide the use of automated video count technology. This study concentrates on a specific algorithm, which would aid in automatic counting. This goal is achieved by following a part-based method, which utilizes the Histogram of Oriented Gradient (HOG) technique as well as a latent support vector machine (SVM). This technique was the preferred algorithm for automation due to its high-speed processing capability and its open source availability. The accuracy of the HOG algorithm in this study is validated using manual counts of pedestrians and cyclists from the collected video data. It is anticipated that the results will assist LTRC-16-4SA in evaluating available count technology options and in identifying preferred alternatives suitable for statewide deployment. The tested algorithm led to accuracy rates between 29-91% for pedestrians and 0-60% for cyclists. Despite the poor results obtained, the algorithm’s efficacy was thoroughly evaluated and documented. Some of the specific challenges faced in this study involved maintaining accurate viewpoint angles as well as conducting object detection in high-density environments and complicated scenes like intersections. New automated video counting systems have sought to improve algorithms in these problematic areas. Future work involves effectively handling these challenges and reevaluating the algorithm while considering others currently being used today.]]></description>
      <pubDate>Mon, 16 Sep 2019 18:00:56 GMT</pubDate>
      <guid>https://trid.trb.org/View/1649298</guid>
    </item>
    <item>
      <title>Virtual-to-Real Knowledge Transfer for Driving Behavior Recognition: Framework and a Case Study</title>
      <link>https://trid.trb.org/View/1640635</link>
      <description><![CDATA[Considering the difficulty and high cost of collecting sufficient data in the real world, driving simulators are used in many studies as an alternative data source, which can provide a much easier and safer way to collect driving data. However, because of the inherent differences between the virtual and real world, the recognition model for driving behavior trained using simulation-based data cannot fit the real driving scenes well. To fill the gap between simulation and real data, a knowledge transfer framework is proposed in this paper. Two transfer learning (TL) methods namely semi-supervised manifold alignment (SMA) and kernel manifold alignment (KEMA) are used in the proposed framework to map the data collected from the virtual and real world to one latent common space. A typical lane-changing scenario is selected for a case study. Three classifiers are trained in the latent space and used to do the lane-changing behavior recognition in the real world. In this way, sufficient simulation data are transferred to supplement the training set with few labeled real data, and thus improve the performance of behavior recognition in the real world. Compared with the traditional methods without knowledge transfer, classifiers combined with TL can reduce the error rate of recognition from around 30% (when only the real data are used) or higher than 50% (when only the simulation data are used) to as low as 11%.]]></description>
      <pubDate>Mon, 16 Sep 2019 17:19:34 GMT</pubDate>
      <guid>https://trid.trb.org/View/1640635</guid>
    </item>
    <item>
      <title>Fault Diagnosis of Train Plug Door Based on a Hybrid Criterion for IMFs Selection and Fractional Wavelet Package Energy Entropy</title>
      <link>https://trid.trb.org/View/1647449</link>
      <description><![CDATA[The train plug door is the only way for passengers getting on and off. Its failures will make train operation ineffective. Taking the developed digital signal processing technologies into consideration, a data-driven diagnosis method for train plug doors is proposed based on sound recognition. First, a novel preprocessing method based on empirical mode decomposition and hybrid intrinsic mode functions (IMFs) selection criterion is proposed. The selected significant IMFs are used to reconstruct the signals. Inspired by the idea of fractional calculus, novel entropy named fractional wavelet package decomposition energy entropy (FWPDE) is proposed. Finally, multi-class support vector machine is used for classification and validation. Experimental results indicate that the proposed preprocessing method is of great significance to extract effective FWPDE features. In addition, FWPDE is more powerful in comparison with the classical wavelet package decomposition energy entropy. The identification accuracy using the proposed method reaches 96.28%, which demonstrates its effectiveness and superiority.]]></description>
      <pubDate>Mon, 16 Sep 2019 17:19:33 GMT</pubDate>
      <guid>https://trid.trb.org/View/1647449</guid>
    </item>
    <item>
      <title>Using GLCM features in Haar wavelet transformed space for moving object classification</title>
      <link>https://trid.trb.org/View/1637735</link>
      <description><![CDATA[This article proposes an integrated system for segmentation and classification of two moving objects, including car and pedestrian from their side-view in a video sequence. Based on the use of grey-level co-occurrence matrix (GLCM) in Haar wavelet transformed space, the authors calculated features of texture data from different sub-bands separately. Haar wavelet transform is chosen because the resulting wavelet sub-bands are strongly affecting on the orientation elements in the GLCM computation. To evaluate the proposed method, the results of different sub-bands are compared with each other. Extracted features of objects are classified by using a support vector machine (SVM). Finally, the experimental results showed that use of three sub-bands of wavelets instead of two sub-bands is more effective and has good precision.]]></description>
      <pubDate>Fri, 30 Aug 2019 13:01:55 GMT</pubDate>
      <guid>https://trid.trb.org/View/1637735</guid>
    </item>
    <item>
      <title>Analyzing variations in spatial critical gaps at two-way stop controlled intersections using parametric and non-parametric techniques</title>
      <link>https://trid.trb.org/View/1642245</link>
      <description><![CDATA[At two-way stop controlled (TWSC) intersections drivers on minor stream are generally at risk because of the difficulty in judging safe gap between major stream vehicles. Any misjudgment by the driver while choosing gap may result in a collision with major stream vehicle. This paper provides important insights for determining and analyzing spatial critical gaps of drivers at high speed and medium speed TWSC intersections. The critical gap line (CGL) fitted for the accepted and rejected gaps using parametric (binary logit model-BLM) and non-parametric (support vector machines-SVM) techniques gives critical gap values at 15th, 50th and 85th percentile speeds. The evaluation of spatial critical gap with respect to major road vehicle (conflicting vehicle) speed makes it easier to understand the impact of variation in speed on spatial gaps accepted by the drivers on the minor road. The logit models developed revealed that the probability of accepting gap decreases with increase in the speed of the conflicting vehicle and it increases with increase in the distance of conflicting vehicle. The spatial critical gaps estimated using support vector machines were found in close approximation with those estimated using binary logit model. The study results showed that SVMs have very good potential to be an alternative tool for the estimation of driver’s critical gap. The spatial critical gaps corresponding to 15th, 50th and 85th percentile speeds for medium speed intersections were 32 m, 38 m and 46 m respectively and for high speed intersections these values were 64 m, 76 m and 104 m respectively. The increase in the magnitude of gap value with respect to the percentile speed clearly states the effect of speed on spatial gaps. The insights from the study can be used to suggest various measures to improve the safety of crossing drivers at uncontrolled intersections.]]></description>
      <pubDate>Fri, 30 Aug 2019 13:01:50 GMT</pubDate>
      <guid>https://trid.trb.org/View/1642245</guid>
    </item>
    <item>
      <title>The Influence of Travel Distance on Mode Share for Regional Trips in China</title>
      <link>https://trid.trb.org/View/1635199</link>
      <description><![CDATA[This paper aims to investigate the influence of travel distance on regional mode share in China. Three regional modes, i.e., road, railway, and air transportation, are considered. Urban characteristics as well as mode share and travel distance data, covering 299 cities around China are covered. The mode shares under different travel distances and urban characteristics are covered and the influence of distance, city size, and economy on mode share are analyzed. Then, four models including linear regression (LR), polynomial regression (PR), artificial neural network (ANN), and support vector machine (SVM), are adopted and calibrated to predict the mode choice likelihood of regional passenger travel distance. The results reveal that travel distance and the urban characteristics strongly affect the regional mode share for all three transportation modes. Also, the improved SVM model performs better for train. This paper is possible to improve accuracy and cost-effectiveness of the existing mode share models.]]></description>
      <pubDate>Fri, 30 Aug 2019 13:01:45 GMT</pubDate>
      <guid>https://trid.trb.org/View/1635199</guid>
    </item>
    <item>
      <title>Detection of Potholes and Speedbumps by Monitoring Front Traffic</title>
      <link>https://trid.trb.org/View/1631088</link>
      <description><![CDATA[This article proposes a novel method for detecting potholes and speed bumps by monitoring the front traffic when the road is not visibly seen. The existing camera-based systems in the car directly scan the road surface and estimate the road profile. The main disadvantage of the current technology is that it is not possible to detect the road profile when the road is not clearly visible. This can happen in situations when roads are waterlogged or have occluded bumps and in low light conditions. In thisarticle, the proposed method for detecting potholes or speed bumps by monitoring the vertical movement of the front traffic can enhance the existing algorithm by overcoming the abovementioned disadvantage. However, the method works only when there is traffic ahead of the system vehicle. The method makes level 3 and above autonomous driving more robust in terms of comfort and safety by estimating the road profile in the abovementioned road conditions. The method uses an object localization algorithm and optical flow to determine the motion vectors of vehicles. The histogram of motion vectors in the vertical direction is calculated and its weighted average is obtained for each frame. As a feature extraction process, fast Fourier transform (FFT) is applied to the fixed size queue buffer containing weighted average values to obtain the frequency spectrum, which is used as a feature set for classification. After feature selection, the support vector machine (SVM) is used to classify whether a pothole/road bump has been detected. Apart from hardware video stabilization, the same classification procedure is applied to static objects in the frame, and camera egomotion is detected. This is done to avoid false positives due to camera movement when the system vehicle is moving over a pothole or a speed bump. The developed algorithm is validated with the manually collected dataset and the results and the analysis are presented here.       ]]></description>
      <pubDate>Thu, 29 Aug 2019 17:30:22 GMT</pubDate>
      <guid>https://trid.trb.org/View/1631088</guid>
    </item>
    <item>
      <title>Hybrid Support Vector Machine Optimization Model for Prediction of Energy Consumption of Cutter Head Drives in Shield Tunneling</title>
      <link>https://trid.trb.org/View/1639242</link>
      <description><![CDATA[The energy consumption of cutter head drives accounts for over half of their total power capacity, and it can reach several thousand kilowatts in shield machines. The analysis of the energy consumption of cutter head drives is thus essential for power planning and control in shield tunneling operations and can help determine shield performance and efficiency. The accurate prediction of energy consumption, which involves complex coupling and nonlinear parameters, has become a challenging task for site managers and tunnel engineers. A hybrid technique that combines least-squares support vector machine (LS-SVM) and particle swarm optimization (PSO) for analyzing energy consumption is proposed in this study. An adaptive Gaussian kernel function–based LS-SVM is used to establish the relationship between energy consumption and identified factors. The parameters of the LS-SVM model can be optimally determined using a nature-inspired intelligent PSO algorithm to improve prediction accuracy. This method is validated in the first Han River Crossing Urban Metro Tunnel Project in China with a complex urban environment. The relative importance of each factor in the PSO-based LS-SVM model is also compared with the results of the sensitivity analysis. Results show that the proposed method can be applied as a feasible and accurate tool for energy consumption audit in urban shield tunneling projects.]]></description>
      <pubDate>Wed, 28 Aug 2019 17:17:14 GMT</pubDate>
      <guid>https://trid.trb.org/View/1639242</guid>
    </item>
    <item>
      <title>Online wavelet least-squares support vector machine fuzzy predictive control for engine lambda regulation</title>
      <link>https://trid.trb.org/View/1625554</link>
      <description><![CDATA[A novel online wavelet least-squares support machine fuzzy predictive control for engine lambda regulation is presented in this article. The prediction model of the proposed online wavelet least-squares support machine fuzzy predictive control is built and updated with a newly proposed modelling algorithm, namely, online wavelet least-squares support machines. The proposed online wavelet least-squares support machine adopts wavelet function that can inherit the local analysis ability and feature extraction from the wavelet transformation, as well as a novel online incremental and decremental updating procedure that can maintain the built prediction model to be accurate, sparse and updated without losing the generalization by continually adding the latest useful data and pruning out the outdated data. Besides, an advanced fuzzy optimizer is proposed to determine the optimal control signal for the online wavelet least-squares support machine fuzzy predictive control, which is faster than the traditional optimizers. The proposed online wavelet least-squares support machine fuzzy predictive control was implemented on a real performance test car and compared with the latest lambda control techniques based on various modelling algorithms, optimizers, updating procedure and support vector kernel for evaluating the effectiveness. The experimental results show that the proposed online wavelet least-squares support machine fuzzy predictive control is a promising scheme for lambda regulation.]]></description>
      <pubDate>Fri, 23 Aug 2019 10:58:14 GMT</pubDate>
      <guid>https://trid.trb.org/View/1625554</guid>
    </item>
    <item>
      <title>Statistical Characteristic-Based Road Structure Recognition in Automotive FMCW Radar Systems</title>
      <link>https://trid.trb.org/View/1633496</link>
      <description><![CDATA[This paper proposes an efficient road structure recognition method using statistical characteristics of received signals in automotive frequency-modulated continuous wave radar systems. Generally, roads consist of various structures, some of which, such as tunnels and soundproof walls made of iron, generate undesired echoes, called clutter. When the clutter flows into the radar system, the target detection performance cannot be guaranteed completely. This causes great danger to the driver using the radar function such as adaptive cruise control. Thus, an efficient method to recognize the structures that deteriorate the radar detection performance is desired. Depending on the types of road structures, frequency components of the received signals have distinctive distributions. Focusing on this point, parameters that reflect statistical properties of each distribution are extracted. These parameters can be used as standards for the recognition because they show different values according to the road structures. For more enhanced recognition, the authors use a support vector machine method with a linear classifier or a Gaussian kernel, and the resulting confusion matrices are derived. According to the results, the proposed method successfully classifies the structures with high accuracy. If the recognition of the road structures that degrade radar’s function is performed effectively, the safety of the driver in the radar-equipped vehicle can be ensured by applying additional signal processing or giving a warning message to the driver.]]></description>
      <pubDate>Tue, 30 Jul 2019 09:38:19 GMT</pubDate>
      <guid>https://trid.trb.org/View/1633496</guid>
    </item>
    <item>
      <title>Traffic Crash Forensic Analysis Based on Univariate Feature Selection</title>
      <link>https://trid.trb.org/View/1635233</link>
      <description><![CDATA[In China, determining which party is liable for damages or injuries resulting from a traffic crash involving both a motor vehicle and a cyclist can be challenging. Based on an analysis of traffic crash data, this paper has proposed a univariate feature selection method which can emulate human thinking and help determine the moving status of the cyclist prior to the collision. This research employed support vector machines (SVM), LDA, and artificial neural network (ANN) to classify the moving status of the cyclists. According to the analysis results, the SVM (kernel=linear) had the highest classification accuracy (81.84%). It could be used to determine if the cyclist was walking the bicycle prior to the collision.]]></description>
      <pubDate>Mon, 22 Jul 2019 10:32:18 GMT</pubDate>
      <guid>https://trid.trb.org/View/1635233</guid>
    </item>
    <item>
      <title>Real-Time Freeway Traffic State Estimation Based on the Second-Order Divided Difference Kalman Filter</title>
      <link>https://trid.trb.org/View/1604301</link>
      <description><![CDATA[Reliable road traffic state identification systems should be designed to provide accurate traffic state information anywhere and anytime. In this paper we propose a road traffic classification system, based on traffic variables estimated using the second order Divided Difference Kalman Filter (DDKF2). This filter is compared with the Extended Kalman Filter (EKF) using both simulated and real-world dataset of highway traffic. Monte-Carlo simulations indicate that the DDKF2 outperforms the EKF filter in terms of parameters estimation error. The real-word evaluation of the DDKF2 filter in terms of classification rate confirms that this filter is promising for real-world traffic state identification systems.]]></description>
      <pubDate>Mon, 22 Jul 2019 07:59:34 GMT</pubDate>
      <guid>https://trid.trb.org/View/1604301</guid>
    </item>
    <item>
      <title>Drivable path detection based on image fusion for unmanned ground vehicles</title>
      <link>https://trid.trb.org/View/1627935</link>
      <description><![CDATA[Autonomous vehicles are used for a range of tasks, such as automated highway driving, transporting work, etc. These vehicles are used both in structured and unstructured environments. This work presents an effective method for path detection using statistical texture features extracted from fused LIDAR sensor and visual camera images. An edge-based feature detection approach is adopted for image registration. The Grey Level Co-occurrence Matrix (GLCM)-based texture features are extracted from the fused image. Classification performance of K-NN and Support Vector Machine (SVM) classifiers are analysed in this work. For experimentation, the data available in Ford Campus Vision data set are used. The results of this new approach are very promising for path detection problem of unmanned ground vehicles.]]></description>
      <pubDate>Fri, 07 Jun 2019 17:29:04 GMT</pubDate>
      <guid>https://trid.trb.org/View/1627935</guid>
    </item>
  </channel>
</rss>