In the future smart transportation system, reliable vehicle-to-infrastructure (V2I) communication is very important to ensure vehicle driving safety and to improve vehicle driving efficiency. In this paper, V2I channel measurements at 5.92 GHz are conducted in typical urban and highway scenarios. The frequency and bandwidth of transmission, as well as the deployment of the RSU (roadside unit) and the OBU (on board unit), are selected by considering the recommendation proposed by 3GPP TR 36.885. Then, based on the measured data, the key channel characteristic parameters of the V2I channel are extracted, including path loss, root-mean-square delay spread, stationarity distance, and Doppler spread, etc. Also, the statistical characteristics of the parameters, including time-varying and Doppler characteristics, are investigated and characterized. The work in this paper helps researchers design technology and communication systems in similar scenarios.

Online reviews on E-commerce platforms contain users’ opinions and emotions about the purchased products. How to enable machines to understand the semantics of review texts and judge their emotional tendencies has become a hot topic of common concern in academia and industry. However, review texts often come from various domains in practical applications, thus there are differences in the description and emotional vocabulary. In this case, traditional classification models trained on review texts from a single domain often have poor classification results. This paper proposes a cross-domain discriminative subspace classification (CDDSC) algorithm based on domain adaptation and subspace learning. First, we adopt the progressive data projection strategy from different domains sequentially into the low-rank subspace and label space, which can reduce the interference of useless information on classification task while mining the global structure of data in each domain. Second, to reduce domain differences, we adopt the dual metric techniques, i.e., maximum mean discrepancy (MMD) based on marginal distribution and MMD based on conditional distribution to approximate the inter-domain overall probability distributions and the inter-domain conditional probability distributions, respectively. Thirdly, we use the slack label and low-rank constraint technique to promote inter-class interval and intra-class tightness. We conduct experiments with several review text corpus oriented Chinese E-commerce platforms. Experiments results show that the CDDSC algorithm obtains good sentiment classification accuracy on Chinese E-commerce platforms.

Interactive data generated by Internet of Things (IoT) devices provides a strong foundation for advancing artificial intelligence. However, the transmission of IoT data poses significant challenges, particularly with respect to privacy protection and communication efficiency. Federated learning (FL), which enables collaborative model training without direct data sharing, has emerged as a promising solution to these challenges. Nevertheless, since data are collected from heterogeneous IoT devices, feature shift inevitably arises across clients, thereby degrading the performance of FL. Although existing studies have made progress in alleviating this issue, few have explored solutions from the perspective of normalization. To address this gap, we propose FL framework via Transformer with agile normalization (FedTAN), a transformer framework with agile normalization, designed to mitigate feature shift among clients by exploiting the intrinsic strengths of transformers in handling non-IID data. Specifically, FedTAN introduces a dynamic Tanh (DyT) activation function to replace conventional normalization layers in the transformer, thereby reducing communication overhead while preserving model performance. Furthermore, FedTAN incorporates statistical information aggregated from the federation to perform randomized normalization on client data and constructs client-specific DyT layers to adaptively mitigate interclient feature shift. Notably, FedTAN not only personalizes a transformer model for each client but also alleviates the adverse impact of federated aggregation on the self-attention mechanism. Extensive experiments under feature shift scenarios demonstrate that FedTAN achieves state-of-the-art performance.

In the rapidly evolving landscape of social media, the demand for precise sentiment analysis (SA) on multimodal data has become increasingly pivotal. This paper introduces a sophisticated data lake architecture tailored for efficient multimodal emotion feature extraction, addressing the challenges posed by diverse data types. The proposed framework encompasses a robust storage solution and an innovative SA model, multilevel spatial attention fusion (MLSAF), adept at handling text and visual data concurrently. The data lake architecture comprises five layers, facilitating real‐time and offline data collection, storage, processing, standardized interface services, and data mining analysis. The MLSAF model, integrated into the data lake architecture, utilizes a novel approach to SA. It employs a text‐guided spatial attention mechanism, fusing textual and visual features to discern subtle emotional interplays. The model’s end‐to‐end learning approach and attention modules contribute to its efficacy in capturing nuanced sentiment expressions. Empirical evaluations on established multimodal sentiment datasets, MVSA‐Single and MVSA‐Multi, validate the proposed methodology’s effectiveness. Comparative analyses with state‐of‐the‐art models showcase the superior performance of our approach, with an accuracy improvement of 6% on MVSA‐Single and 1.6% on MVSA‐Multi. This research significantly contributes to optimizing SA in social media data by offering a versatile and potent framework for data management and analysis. The integration of MLSAF with a scalable data lake architecture presents a strategic innovation poised to navigate the evolving complexities of social media data analytics.

A compact dual wavelength Nd:YVO₄/MgO:PPLN infrared laser was developed successfully which was composed of Nd:YVO₄ crystal, MgO:PPLN crystal and a cavity mirror(M1). The fundamental laser was consisted of the first face of Nd:YVO₄ and M1, and the optical parametric oscillation(OPO) cavity defined by the second face of Nd:YVO₄ and M1. The infrared laser output with wavelengths of 1539 nm and 3447 nm was obtained using intracavity cw OPO technology. The output power of 1539nm and 3447nm were 670mW and 236mW at the pumped LD power of 6.0 W, and the optical conversion efficiency was 15.1%. The higher conversion efficiency was mainly attributed the 2mm thickness of MgO:PPLN crystal. Intracavity dual wavelength laser can be used in spectrum detection, drunk driving test and so on.

Introduction Dynamic monitoring of health behaviors in adolescent sports is crucial for promoting healthy growth. Traditional monitoring methods, however, suffer from limitations such as incomplete data acquisition, low analysis efficiency, and poor sustainability. This study addresses these issues by proposing a dynamic monitoring system for adolescent sports and health behaviors. Methods The proposed system utilizes multi-source sensor data and image extraction algorithms. A novel multimodal feature fusion algorithm based on depth motion images (DMIs) was developed for efficient sports action recognition and anomaly analysis. Depth data was converted into DMIs, and inertial data into signal images. Both image types were processed using local ternary pattern (LTP) to generate multimodal input data. Convolutional neural networks (CNNs) were used to extract features from each modality. Feature-level fusion was then performed using discriminant correlation analysis (DCA) to maximize feature correlation between modalities and minimize feature correlation within modalities and between categories. Finally, fused features were classified using a multi-class support vector machine (SVM) to achieve efficient motion behavior recognition and analysis. Results The experimental results demonstrate that the proposed system achieved a recognition accuracy exceeding 90% in classifying five adolescent sports behaviors. This performance surpassed that of other comparative algorithms. Furthermore, the method achieved competitive recognition accuracy across the evaluated action categories, demonstrating its applicability and robustness in complex scenarios. Discussion The findings of this study offer new insights and methodologies for monitoring and intervening in adolescent sports health behaviors. The proposed system and algorithms provide technical support for the sustainable design of dynamic monitoring systems in this field.