3D semantic segmentation remains a pivotal challenge for autonomous driving due to the inherent sparsity of points. Existing CNN-based and Transformer-based methods struggle with either limited receptive fields or quadratic computational complexity. Although some Mamba-based 3D models are designed efficiently with linear complexity, they often overlook the long-term decay problem in Selective State-space Models when processing extremely long sequences in large-scale scenes. In this paper, we propose a Hierarchical Bi-directional Mamba (HB-Mamba) for point cloud semantic segmentation. By decoupling feature extraction into a Global Memory branch and a Local Detail branch, our architecture effectively captures long-range semantics and preserves fine-grained geometric information. Besides, we further introduce a Spatial-Channel Fusion Block to dynamically fuse these multi-scale representations. Experimental results on the nuScenes-Lidarseg benchmark demonstrate that HB-Mamba achieves state-of-the-art performance among Lidar-only methods, reaching 82.8% mIoU on the test set and 81.33% mIoU on the validation set, outperforming the leading transformer-based model PTv3 by 0.1% and 1.01%, respectively.

Understanding the environment and a robot’s physical reachability is crucial for task execution. While state-of-the-art vision-language models (VLMs) excel in environmental perception, they often generate inaccurate or impractical responses in embodied visual reasoning tasks due to a lack of understanding of robotic physical reachability. To address this issue, we propose a unified representation of physical reachability across diverse robots, i.e., Space-Physical Reachability Map (S-P Map), and PhysVLM, a vision-language model that integrates this reachability information into visual reasoning. Specifically, the S-P Map abstracts a robot’s physical reachability into a generalized spatial representation, independent of specific robot configurations, allowing the model to focus on reachability features rather than robot-specific parameters. Subsequently, PhysVLM extends traditional VLM architectures by incorporating an additional feature encoder to process the S-P Map, enabling the model to reason about physical reachability without compromising its general vision-language capabilities. To train and evaluate PhysVLM, we constructed a large-scale multi-robot dataset, Phys100K, and a challenging benchmark, EQA-phys, which includes tasks for six different robots in both simulated and real-world environments. Experimental results demonstrate that PhysVLM outperforms existing models, achieving a 14% improvement over GPT-4o on EQA-phys and surpassing advanced embodied VLMs such as RoboMamba and SpatialVLM on the RoboVQA-val and OpenEQA benchmarks. Additionally, the S-P Map shows strong compatibility with various VLMs, and its integration into GPT-4o-mini yields a 7.1% performance improvement.

3D object detection aims to locate and recognize the object from the point cloud, which is a meaningful and foundation task in autonomous driving. However, the sparsity of the point cloud poses a significant challenge for this task, especially for distant and small objects. Existing methods employ depth estimation networks to generate pseudo points for improving the point density, but this introduces significant computational costs and noise, limiting performance gains. In this paper, we propose the Semantic-aware Fine-grained Point Augmentation (SFPA) approach for 3D object detection, which simultaneously enriches high-quality point clouds and filters noisy points, and incorporates multi-modal feature fusion to enhance detection performance. Specifically, we utilize a semantic segmentation model to generate object masks from RGB images and refine dense depth estimation maps, derived from sparse LiDAR points and RGB images, using these foreground object masks. Subsequently, high-quality pseudo point clouds, concentrated solely on foreground objects, are generated by projecting the refined dense depth maps back to 3D coordinates. Furthermore, we also employ the projection matrix as an alignment strategy to concatenate or add dense RGB features with point features, further improving detection performance for extremely sparse objects. Experimental results demonstrate that our method achieves state-of-the-art performance on KITTI 3D object detection leaderboard, i.e., 95.44%, 88.18%, 85.53% for the Car category at the easy, medium, and hard levels, respectively.

In recent years, lightweight large language models (LLMs) have garnered significant attention in the robotics field due to their low computational resource requirements and suitability for edge deployment. However, in task planning—particularly for complex tasks that involve dynamic semantic logic reasoning—lightweight LLMs have underperformed. To address this limitation, we propose a novel task planner, LightPlanner, which enhances the performance of lightweight LLMs in complex task planning by fully leveraging their reasoning capabilities. Unlike conventional planners that use fixed skill templates, LightPlanner controls robot actions via parameterized function calls, dynamically generating parameter values. This approach allows for fine-grained skill control and improves task planning success rates in complex scenarios. Furthermore, we introduce hierarchical deep reasoning. Before generating each action decision step, LightPlanner thoroughly considers three levels: action execution (feedback verification), semantic parsing (goal consistency verification), and parameter generation (parameter validity verification). This ensures the correctness of subsequent action controls. Additionally, we incorporate a memory module to store historical actions, thereby reducing context length and enhancing planning efficiency for long-term tasks. We train the LightPlanner-1.5B model on our LightPlan-40k dataset, which comprises 40,000 action controls across tasks with 2 to 13 action steps. Experiments demonstrate that our model achieves the highest task success rate despite having the smallest number of parameters. In tasks involving spatial semantic reasoning, the success rate exceeds that of ReAct by 14.9%. Moreover, we demonstrate LightPlanner’s potential to operate on edge devices.

Visual reasoning in multimodal large language models (MLLMs) has primarily been studied in passive, static settings, limiting their effectiveness in real-world physical environments where an embodied agent must contend with incomplete information due to occlusion or a limited field of view. Humans, in contrast, leverage their embodiment to actively explore and interact with their environment—moving, examining, and manipulating objects—to gather information through a closed-loop process integrating perception, reasoning, and action. Inspired by this capability, we introduce the Active Visual Reasoning (AVR) task, extending visual reasoning to a paradigm of embodied interaction in partially observable environments. AVR necessitates embodied agents to: (1) actively acquire information via sequential physical actions, (2) integrate observations across multiple steps for coherent reasoning, and (3) dynamically adjust decisions based on evolving visual feedback. To rigorously evaluate AVR, we introduce CLEVR-AVR, a simulation benchmark featuring multi-round interactive environments designed to assess both reasoning correctness and information-gathering efficiency. We present AVR-152k, a large-scale dataset that offers rich Chain-of-Thought (CoT) annotations detailing iterative reasoning for uncertainty identification, action-conditioned information gain prediction, and information-maximizing action selection, crucial for training agents in a higher-order Markov Decision Process. Building on this, we develop PhysVLM-AVR, an embodied MLLM achieving state-of-the-art performance on CLEVR-AVR, embodied reasoning (OpenEQA, RoboVQA), and passive visual reasoning (GeoMath, Geometry30K). Our analysis also reveals that current embodied MLLMs, despite detecting information incompleteness, struggle to actively acquire and integrate new information through interaction, highlighting a fundamental gap in active reasoning capabilities.

Sensors are widely deployed on high-speed trains for real-time operational status monitoring. The integrity of multi-sensor signals over time is critical for the train’s Prognostics and Health Management (PHM) system. However, data missing during multi-sensor signal acquisition and transmission can severely limit the performance of PHM systems. Therefore, this paper proposes a novel Conditional Time Series Diffusion (CTSDiff) model designed for efficient and accurate imputation of missing values in high-speed trains’ multi-sensor time series signals. Firstly, CTSDiff utilizes the non-missing sensor signals collected as conditional information to guide missing data generation, thereby achieving data imputation. Secondly, CTSDiff employs one-dimensional convolutional residual blocks with dilation parameters to capture complex temporal dependencies and adopts a skip-step non-Markovian sampling process to accelerate the imputation procedure. Finally, experimental results demonstrate that CTSDiff can generate high-quality and diverse imputations across various missing data scenarios. The imputation data provided by CTSDiff ensures consistency with actual data distribution and obtains confidence information of the imputed data, significantly enhancing the integrity of multi-sensor signals in high-speed trains and the accuracy of intelligent analysis within PHM systems. Notably, this study opens new avenues for addressing missing data issues in high-speed train multi-sensor datasets and showcases the great potential of diffusion models in generating sensor signals.

Vehicular Edge Computing and Networks (VECoNs) have gained popularity for its enhanced Internet of Vehicles (IoV) capabilities. To satisfy the needs of delay-sensitive and computation-intensive in-vehicle applications, VECoNs need to provide low-latency task offloading services. However, existing offloading frameworks generally overlook the spatially and temporally heterogeneous computation task arrival patterns. The former causes overloading and underloading of RSU computational resources and thus hinders further reduction of offloading latency on the macro-scale, while the latter emphasizes the importance of long-term system performance, especially energy constraints, posing challenges to the design of offloading framework and optimization strategies. This paper introduces a novel distributed two-stage task offloading architecture based on Lyapunov and multi-agent deep deterministic policy gradient (MADDPG). On one hand, it jointly optimizes the initial offloading stage within VEC subsystems and the RSU peer offloading stage to minimize offloading delays for each VEC subsystem. On the other hand, it incorporates RSU energy consumption within long-term constraints to formulate the offloading optimization problem. After decoupling the energy coupling between RSU time slots using the Lyapunov algorithm, a Lyapunov and MADDPG-based distributed task offloading (LAMETO) algorithm is presented to solve the optimal problem in a distributed manner. Simulation results show that the proposed framework and algorithm can reduce the system delay, energy consumption, and energy deficit while stabilizing convergence.

The health monitoring of traction motors is crucial for the prognostics and health management of high-speed trains. The temperature signal is an outstanding health indicator. Due to the representing of the traction motor's health conditions and low cost, accurate prediction for the motor temperature is conducive to early detection of abnormalities. However, the traditional prediction models are trained offline with high dependency on training data and cannot adapt to varying distributions of real data timely. Therefore, over time, the accuracies of these models always decrease noticeably. Concerning this issue, we propose an online health monitoring framework for traction motors using temperature signals. First, in the offline phase, multisensor signals are utilized to develop a generalized prediction model to absorb extensive information from temperature and relevant signals. Second, during the online phase, the training parameters are dynamically estimated to fulfill individualized learning by adopting a combination of the sample complexity and real-time prediction errors so as to fulfill individualized training according to the monitored data samples. Furthermore, a low-regret strategy is also presented in the online phase to determine the optimization target of the model to make the online update adaptive enough to the online prediction task. Consequently, the model can obtain new knowledge and greater understanding about the real data by online-learning continuously. Finally, the proposed framework is verified by actual data collected from Chinese high-speed trains. Compared with the conventional multilayer perceptron, gated recurrent unit, and long short-term memory, new patterns of stream data can be captured and adapted by using our framework, and the average root mean square errors of prediction results are reduced by 5%, 12%, and 11%, the average mean absolute percentage errors are reduced by 10%, 12%, and 11%, respectively. It is proven that our framework has high prediction accuracy and well-performed adaptability on real datasets.

Vehicle re-identification (Re-ID) aims at finding the target vehicle identity from multi-camera surveillance videos, which plays an important role in the intelligent transportation system (ITS). It suffers from the subtle discrepancy among vehicles from the same vehicle model and large variation across different viewpoints of the same vehicle. To enhance the robustness of Re-ID models, many methods exploit additional detection or segmentation models to extract discriminative local features. Some others employ data-driven methods to enrich the diversity of the training data, such as the data augmentation and 3D-based data generation, so that the Re-ID model can obtain stronger robustness against intra-class variations. However, these methods either rely on extra annotations or greatly increase the computational cost. In this paper, we propose the Bi-level Implicit semantic Data Augmentation (BIDA) framework to solve this problem from two aspects. (1) We implicitly augment the images semantically in the feature space according to the identity-level and superclass-level intra-class variations, which can generate more diverse semantic augmentations beyond the intra-identity variations. (2) We introduce the similarity ranking constraints on the augmented training set by extending the sample-wise triplet loss to the distribution-wise one, which can effectively reduce meaningless semantic transformations and improve the discrimination of the feature. We conduct extensive experiments on VeRi-776, VehicleID and Cityflow benchmarks to reveal the effectiveness of our method. And we achieve new state-of-the-art performance on VeRi-776.

High-speed train bogies are the critical components of high-speed trains, which can play the role of traction, braking, and buffering. In long-term train service, bogies are prone to wear and aging. Currently, most studies on fault diagnosis methods are aimed at single equipment identification. It is challenging to accurately diagnose the faults of such coupled multi-equipment combination systems as bogies. Multiple devices on the bogie have implied correlations in space, and fully exploiting their spatial features enhances the fault diagnosis accuracy. This paper proposes a new bogie fault diagnosis method based on the directional graph of train bogie: RS-GAT model. The model uses the Residual-Squeeze Network (RS-Net) to construct the framework of the model and use the Graph Attention Network (GAT) for spatial information fusion and feature extraction to identify bogie faults. Using six datasets collected under the operation of high-speed trains, experimental results demonstrate that the proposed approach has better effectiveness than the RS-Net class model and single-layer graph class model, with diagnosis accuracy near 96%. Ablation experiments and comparisons between RS-GAT and RS-GCN verify the effectiveness of RS-Net framework and GAT model in fault classification. In addition, the RS-GAT model is found to have strong robustness when different models are analyzed using small-scale data sets.

Turnouts are crucial to the safety of high-speed railways. Due to the intensive use and complex environment, breakdowns caused by different faults occur frequently in practice. Considering that the operation of turnouts is a multi-stage process during which each stage has its specific health characteristics, this paper proposes segmentalized maximal-relevancy and minimal-redundancy (mRMR) for feature extraction from each stage separately. Based on mathematical analysis of the turnout mechanism, the electric power curve is segmented into four stages, from which time-domain analysis and mRMR are combined to extract valid features corresponding to different movements respectively. Then, a novel classifier named cost-sensitive Extreme Learning Machine with fixed inputs (cf-ELM) is proposed for fault classification. We modify the inputs of ELM and define a new formula to limit the input weights and biases for the sake of stability of the network structure. Besides, a cost-sensitive optimization method is also presented in this classifier to embed the failure degree and data proportion into cost calculation rules to deal with data imbalance. To verify our proposed method, real data collected from a turnout of Beijing-Shanghai high-speed railway is used. It is proven by comparisons that the accuracy of our method has achieved 100% with fast running speed and also outperforms traditional methods in terms of stability and generalization remarkably.

Fault diagnosis of wheelset bearings in high-speed trains has attracted constant interest in the scientific community and industrial field. Under the harsh working condition, e.g., time-varying speed and load, most existing methods are hindered by the limited and unknown situations of wheelset bearings. Although the self-calibrated convolution is proven to effectively expand the receptive field with more accurate discriminative regions, its use in fault diagnosis still lacks needed physical interpretation as well as computational efficiency. To this end, this article presents a novel framework by using the logarithmic short-time Fourier transform and the modified self-calibrated convolution. It first manifests a time-frequency map that has explicit physics meaning while reducing the gap between high energy and detailed characteristics in the masking of interfering signals. To simplify redundant kernels, a modified self-calibrated residual block is proposed without introducing any more parameters, while preserving an interpretable and simple structure. The effectiveness and robustness of the proposed method are verified by the experimental data collected from an industrial railway axle bearing test rig. Results are found superior to those of five state-of-art methods, which are more practical in terms of accuracy, cost time, and model size.

The multi-hop protocols are proved effective in the railway disaster wireless monitoring system. However, farther transmission distance with the larger data will decline the valid lifetime and reliability of the system. Most existing studies focused primarily on the communication protocols optimization, and some works tried to utilize the limited computation ability at the network-level or node-level, which are insufficient for the stiff disaster information monitoring demands. This paper presents an adaptive hybrid computation and communication strategy to fully taking advantage of the sensor processing ability, and improve the energy efficiency at the link-level. Furthermore, an adaptive optimization model is designed to meet the different monitoring demands of the system, and the valid lifetime is improved accordingly. Numerical examples with various operational scenarios are developed to demonstrate the superiority and practicality of the proposed protocol in the lifetime improvement, energy consumption minimization and equalization compared with other outstanding protocols.

The bogie system is a critical system for a high-speed train, which is composed of various mechanical parts. Therefore, the health of the bogie can directly affect the health of high-speed train. Temperature signals, speed signals and pressure signals are collected from the bogie can reflect its health. Hence, the multi-sensor fault diagnosis methods can provide novel solutions for the bogie health monitoring tool. This paper presents a novel bogie fault diagnosis scheme named the AttGGCN model, using graph convolutional network (GCN), gated recurrent unit (GRU) and attention mechanism. In this fault diagnosis scheme, the bogie data network is established firstly. Then, temporal and spatial features are extracted and fused using GCG unit. Finally, the GCN are used for fault identification. Twenty-four kinds of measured signals and seven types of faults from actual High-speed train in operation are utilized for verification. Results show that the AttGGCN model has the highest accuracy compared to conventional models. In addition, experiments on different scales of training sets suggest that the AttGGCN model has strong robustness in small-scale datasets. Besides, ablation experiments certificate that the attention mechanism is able to strengthen the feature extraction ability.

Energy efficiency of wireless sensors is critical to maintaining the function of the monitoring system. Generally, the energy consumed in data transmission is much larger than in compression. Hence, decreasing data packet size with the aid of data compression before transmission can facilitate the reduction of energy consumption in communication. However, the energy consumed in data computation is also considerable, and improper computation ways may incur more energy consumption. To address this issue, in this article, two-hierarchy communication and computation hybrid optimization protocol is presented to minimize the total energy consumption. First, the cluster heads (CHs) rotation and clusters updating strategies are proposed in the communication layer, and the optimized adaptive compression ratios for the CHs are adopted in the computation layer. The hybrid optimization scheme is performed from the views of communication and computation synergistically to improve energy efficiency. The simulation results show the superiority of the proposed protocol compared with other outstanding protocols.

Automatic operation of high speed trains (HSTs) requires dedicated control schemes to tackle uncertain dynamics, unknown resistive forces, coupling nonlinearities, interactive in-train forces, unexpected disturbances, and faults. This paper addresses the problem of position and velocity tracking control of HSTs with multiple vehicles connected through elastic couplers. A neuro-adaptive fault tolerant control scheme is developed to compensate the input nonlinearities due to traction or braking notches, uncertain impacts from in-train forces, resistive aerodynamic drag forces, traction or braking faults, and adherence-antiskid constraints. High precision velocity and position tracking is achieved by using the proposed control scheme that combines the robust adaptive control with nonlinearly layered neural networks. Closed-loop stability is ensured with strict mathematical analysis. The effectiveness of the proposed approach is also validated through numerical simulations with considering the adherence-antiskid constraints.

The multi-hop communication protocol can balance the energy consumption of sensors to extend the service lifetime in high-speed railways (HSRs). However, the communication via multiple hops will increase the data transmission latency. Most previous studies have focused on optimizing either the sensor network lifetime or the data transmission latency but have not considered both. This paper presents an adaptive multi-objective optimization model for multi-hop communication systems. This model explicitly addresses the trade-off between the lifetime and the latency associated with the use of network-level wireless condition monitoring systems for ensuring the railway operational safety. Numerical examples with various operational scenarios are developed to demonstrate the superiority and practicality of the proposed approach. Compared with the three previously applied protocols, the proposed approach can achieve longer sensor network lifetime, shorter data latency, and greater system utility (accounting for both lifetime and latency). This paper provides the technical support for the development of stable and reliable wireless monitoring management systems for HSR safety.

A wireless monitoring network is an effective way to monitor and transmit information about railway infrastructure conditions. Its lifetime is significantly affected by the energy usage among all sensors. This paper proposes a novel cluster-based valid lifetime maximization protocol (CVLMP) to extend the lifetime of the network. In the CVLMP, the cluster heads (CHs) are selected and rotated with the selection probability and energy information. Then, the clusters are determined around the CHs based on the multi-objective optimization model, which minimizes the total energy consumption and balances the consumption among all CHs. Finally, the multi-objective model is solved by an improved nondominated sorting genetic algorithm II. The simulation results show that, compared with two other strategies in the prior literature, our proposed CVLMP can effectively extend the valid lifetime of the network as well as increase the inspected data packets received at the sink node.

The wireless monitoring system is always destroyed by the insufficient energy of the sensors in railway. Hence, how to optimize the communication protocol and extend the system lifetime is crucial to ensure the stability of system. However, the existing studies focused primarily on cluster‐based or multihop protocols individually, which are ineffective in coping with the complex communication scenarios in the railway wireless monitoring system (RWMS). This study proposes a hybrid protocol which combines the cluster‐based and multihop protocols (CMCP) to minimize and balance the energy consumption in different sections of the RWMS. In the first hierarchy, the total energy consumption is minimized by optimizing the cluster quantities in the cluster‐based protocol and the number of hops and the corresponding hop distances in the multihop protocol. In the second hierarchy, the energy consumption is balanced through rotating the cluster head (CH) in the subnetworks and further optimizing the hops and the corresponding hop distances in the backbone network. On this basis, the system lifetime is maximized with the minimum and balance energy consumption among the sensors. Furthermore, the hybrid particle swarm optimization and genetic algorithm (PSO‐GA) are adopted to optimize the energy consumption from the two‐layer hierarchy. Finally, the effectiveness of the proposed CMCP is verified in the simulation. The performances of the proposed CMCP in system lifetime, residual energy, and the corresponding variance are all superior to the LEACH protocol widely applied in the previous research. The effective protocol proposed in this study can facilitate the application of the wireless monitoring network in the railway system and enhance safety operation of the railway.

Snow detection and removal from video images is very challenging. Normally the snowflakes affect only on a very small region of an image, hence the confusion to determine which region should be considered and which one should not. In this paper, a frame difference method with five successive frames is first presented to detect the snow pixels from image background, but the method didn't work well in the case of heavy snow. Then a new technique has been implemented which uses the L0gradient minimization approach to remove the snow pixels. This technique can control how many non-zero gradients are resulted in the image, and is independent of local features, but instead locates important edges globally. These salient edges are preserved and the low amplitude and insignificant details are diminished. The snow pixels are then removed in this way. Experimental results show that this method is a highly efficient algorithm even under heavy snow conditions, while preserving the details of the image.

The realization of road traffic prediction not only provides real-time and effective information for travelers, but also helps them select the optimal route to reduce travel time. Road traffic prediction offers traffic guidance for travelers and relieves traffic jams. In this paper, a real-time road traffic state prediction based on autoregressive integrated moving average (ARIMA) and the Kalman filter is proposed. First, an ARIMA model of road traffic data in a time series is built on the basis of historical road traffic data. Second, this ARIMA model is combined with the Kalman filter to construct a road traffic state prediction algorithm, which can acquire the state, measurement, and updating equations of the Kalman filter. Third, the optimal parameters of the algorithm are discussed on the basis of historical road traffic data. Finally, four road segments in Beijing are adopted for case studies. Experimental results show that the real-time road traffic state prediction based on ARIMA and the Kalman filter is feasible and can achieve high accuracy.

In this paper, a novel bacterial foraging algorithm (BFA)-Gaussian support vector classifier machine (GSVCM) model was proposed to improve the fatigue classification accuracy of electromyography (EMG) signals. This optimization mechanism involves the kernel parameter setting in the GSVCM training procedure, which significantly influences the classification accuracy. Experiments were conducted based on the EMG signal to differentiate the normal and fatigue status. In the proposed method, the EMG signals were decomposed into intrinsic mode functions by ensemble empirical mode decomposition (EEMD) before the mean instantaneous frequency could be obtained by Hilbert transform (HT). Finally, the fatigue statistical features can be extracted from fast Fourier transform and EEMD-HT. The application of this model to the fatigue status recognition of EMG signal indicated that further significant enhancement of the classification accuracy can be achieved by the proposed BFA-GSVCM classification system. The diagnostic method is effective and feasible.

During these years, mobile telecommunication system based on LTE has been largely studied and has formed a mature technical system. For special application scenarios and business requirement, a comprehensive and new generation of railway mobile telecommunication system based on LTE is bound to take shape via innovative researches and technology improvements. Under fast- moving scenario of high-speed railway, the performance of signal system transmission is severely interfered by OFDM, subcarrier signal frequency shift due to Doppler Effect. Given that, this paper focuses on Doppler Shift estimation for high-speed railway scenario and combines Doppler Shift estimation based on cyclic prefix as well as the estimation based on pilot frequency to propose an improved Doppler Shift estimation so as to raise estimated accuracy and anti- multipath capability.

Accurate real-time crash risk evaluation is essential for making prevention strategy in order to proactively improve traffic safety. Quite a number of models have been developed to evaluate traffic crash risk by using real-time surveillance data. In this paper, the basic idea of traffic safety region is introduced into highway crash risk evaluation. Sequential forward selection (SFS), principal components analysis (PCA) and least squares support vector machine (LSSVM) are used to estimate the traffic safety region and classify the traffic states (safe condition and unsafe condition). The proposed method works by first extracting state variables from the observed traffic variables. Two statistics [Formula: see text] and squared prediction error (SPE) are calculated by SFS–PCA and used as the final state variables for traffic state space. Next, LSSVM is used to estimate the boundary of traffic safety region and identify the traffic states in the traffic state space. To demonstrate the advantage of the proposed method, this study develops two crash risk evaluation models, namely SFS–LSSVM model and PCA–LSSVM model, based on crash data and non-crash data collected on freeway I-880N in Alameda. Validation results show that the method is of reasonably high accuracy for identifying traffic states.

This paper formulates the bandwidth allocation problem in train-to-ground wireless communication networks in operational process of trains. It is shown that the Nash Bargaining game provides an Asymmetric Nash Bargaining Solution which is fair to bandwidth allocation problems in different services. We proposed a bandwidth allocation model for train-to-ground communication system. It can effectively reflect allocation strategies for services with different bargaining power. We define a dynamic adaptive function of bargaining power in order to match utility functions under diverse bandwidths. Easily to implement as it is, an algorithm for bandwidth allocation is derived and then simulated. The simulation show that the proposed scheme has high rate of resource utilization, and is suitable for train-to-ground communication systems.

Mining the data source from a crowd of people has elicited increasing attention in recent years. In existing studies, multiple users are utilized, in which each user is generally required to annotate only one attribute for each sample. However, there are cases in numerous annotation tasks wherein despite of the presence of multiple users, each user should classify or rate multiple attributes for each sample. This situation is referred to as multi-user multi-attribute annotations in this paper. This work deals with the learning problem under multi-user multi-attribute annotations. A generative model is introduced to describe the human labeling process for multi-user multi-attribute annotations. Subsequently, a maximum likelihood approach is leveraged to infer the parameters in the generative model, namely, ground-truth labels, user expertise, and annotation difficulties. The classifiers for each attribute are also learned simultaneously. Furthermore, the correlations among attributes are taken into account during inference and learning using conditional random field. The experimental results reveal that compared with existing methods that ignore the characteristics of multi-user multi-attribute annotations, our approach can obtain better estimation of the ground truth labels, user experts, annotation difficulties as well as attribute classifiers.

Magnetic sensors can be applied in vehicle recognition. Most of the existing vehicle recognition algorithms use one sensor node to measure a vehicle‖s signature. However, vehicle speed variation and environmental disturbances usually cause errors during such a process. In this paper we propose a method using multiple sensor nodes to accomplish vehicle recognition. Based on the matching result of one vehicle‖s signature obtained by different nodes, this method determines vehicle status and corrects signature segmentation. The co-relationship between signatures is also obtained, and the time offset is corrected by such a co-relationship. The corrected signatures are fused via maximum likelihood estimation, so as to obtain more accurate vehicle signatures. Examples show that the proposed algorithm can provide input parameters with higher accuracy. It improves the average accuracy of vehicle recognition from 94.0% to 96.1%, and especially the bus recognition accuracy from 77.6% to 92.8%.

A novel quantization watermarking method is presented in this paper, which is developed following the established feature modulation watermarking model. In this method, a feature signal is obtained by computing the normalized correlation (NC) between the host signal and a random signal. Information modulation is carried out on the generated NC by selecting a codeword from the codebook associated with the embedded information. In a simple case, the structured codebooks are designed using uniform quantizers for modulation. The watermarked signal is produced to provide the modulated NC in the sense of minimizing the embedding distortion. The performance of the NC-based quantization modulation (NCQM) is analytically investigated, in terms of the embedding distortion and the decoding error probability in the presence of valumetric scaling and additive noise attacks. Numerical simulations on artificial signals confirm the validity of our analyses and exhibit the performance advantage of NCQM over other modulation techniques. The proposed method is also simulated on real images by using the wavelet-based implementations, where the host signal is constructed by the detail coefficients of wavelet decomposition at the third level and transformed into the NC feature signal for the information modulation. Experimental results show that the proposed NCQM not only achieves the improved watermark imperceptibility and a higher embedding capacity in high-noise regimes, but also is more robust to a wide range of attacks, e.g., valumetric scaling, Gaussian filtering, additive noise, Gamma correction, and Gray-level transformations, as compared with the state-of-the-art watermarking methods.

An architecture of sensor network for urban traffic information acquisition is proposed. The hybrid communication modes include CAN, ZigBee and Ethernet, which can satisfy the requirements of wired and wireless, real-time and massive data transmission. The various kinds of nodes and the prototype sensor network were developed and deployed in Beijing. The test results show the architecture, hybrid communication mode, various sensor nodes and the sensor network proposed in the paper are practical and feasible. This kind of sensor network can be used in traffic surveillance to resolve the problems of present information acquisition.

The linguistic constraints and phrase-length constraints are the most important factors for Chinese prosodic phrasing in the natural speech. This paper presents a linguistic constraint model and a phrase-length constraint model to describe these two processes independently. Therefore, each part can be described in detail. In the linguistic constraints model, Chunk (base phrase) is considered as an important basic unit. And an HMM is used to model the phrase-length constraints, which concerns the distribution of the prosodic phrase lengths and the relationship between the prosodic phrase and the prosodic words. Then a k-candidate method is introduced to combine these two models. This approach makes full use of the linguistic constraints and the phrase-length constraints. The experiments show that this approach achieved a perfect performance with the phrasing f-score 82.9%.