As a core component of intelligent transportation systems, vehicle localization technology enables accurate positioning, supporting comprehensive insights into traffic flow, vehicle status, and environmental changes. Current vehicle position localization technologies primarily rely on visual sensors and the Global Positioning System, while their performance can be affected by extreme weather conditions and signal stability. However, vehicle-generated sound, as a stable data source unaffected by environmental conditions and free from signal limitations, is often underutilized by existing studies. In this article, we construct a vehicle localization dataset based on sound signals and further propose a combined filtering strategy that integrates adaptive filtering with spectral subtraction filtering, dynamically adjusting the filter parameters to suppress time-correlated noise within the signal. We also remove broadband noise in the frequency domain while preserving high-frequency signal details, offering a significant advantage over existing methods in terms of signal-to-noise ratio improvement. The proposed dataset and filtering strategy are validated using the EfficientNet-1D Fusion model. Experimental results demonstrate that the proposed combined filtering method excels in recognition accuracy and computational efficiency.

Abstract Large Language Models (LLMs) are widely applied in time series analysis. Yet, their utility in few-shot classification—a scenario with limited training data—remains unexplored. We aim to leverage the pre-trained knowledge in LLMs to overcome the data scarcity problem within multivariate time series. To this end, we propose LLMFew, an LLM-enhanced framework, to investigate the feasibility and capacity of LLMs for few-shot multivariate time series classification (MTSC). We first introduce a Patch-wise Temporal Convolution Encoder (PTCEnc) to align time series data with the textual embedding input of LLMs. Then, we fine-tune the pre-trained LLM decoder with Low-rank Adaptations (LoRA) to enable effective representation learning from time series data. Experimental results show our model consistently outperforms state-of-the-art baselines by a large margin, achieving 125.2% and 50.2% improvement in classification accuracy on Handwriting and EthanolConcentration datasets, respectively. Our results also show LLM-based methods achieve comparable performance to traditional models across various datasets in few-shot MTSC, paving the way for applying LLMs in practical scenarios where labeled data are limited. Our code is available at https://github.com/junekchen/llm-fewshot-mtsc .

Compared to feature or decision fusion, hybrid fusion can beneficially improve audio-visual speech recognition accuracy. Existing works are mainly prone to design the multi-modality feature extraction process, interaction, and prediction, neglecting useful information on the multi-modality and the optimal combination of different predicted results. In this paper, we propose a multi-scale hybrid fusion network (MSHF) for mandarin audio-visual speech recognition. Our MSHF consists of a feature extraction subnetwork to exploit the proposed multi-scale feature extraction module (MSFE) to obtain multi-scale features and a hybrid fusion subnetwork to integrate the intrinsic correlation of different modality information, optimizing the weights of prediction results for different modalities to achieve the best classification. We further design a feature recognition module (FRM) for accurate audio-visual speech recognition. We conducted experiments on the CAS-VSR-W1k dataset. The experimental results show that the proposed method outperforms the selected competitive baselines and the state-of-the-art, indicating the superiority of our proposed modules.

Compared to relying only on audio information, incorporating visual information improves speech recognition accuracy in noisy environments. Existing works are prone to design specific architecture for feature extraction, neglecting feature enhancement. In this paper, we propose an end-to-end Mandarin audio-visual speech recognition model with a Feature Enhancement Module. Specifically, we design a Feature Enhancement Module (FEM) that uses deconvolution and up-sampling to obtain the twin enhanced data for generating high-resolution feature representation. We further develop the Visual Feature Enhancement Module (Visual FEM) and Audio Feature Enhancement Module (Audio FEM) to enhance feature extraction from both visual data and audio data. We incorporate the proposed modules into the blocks of the Residual Network for accurate audio-visual speech recognition. We conducted experiments on the CAS-VSR-W1k and Chinese Mandarin Lip Reading (CMLR) datasets. The experimental results show that the proposed method outperforms the selected competitive baselines and the state-of-the-art, indicating the superiority of our proposed modules.

The session-based recommendation aims to predict users' immediate next actions based on their short-term behaviors reflected by past and ongoing sessions. Graph neural networks (GNNs) recently dominated the related studies, yet their performance heavily relies on graph structures, which are often predefined, task-specific, and designed heuristically. Furthermore, existing graph-based methods either neglect implicit correlations among items or consider explicit and implicit relationships altogether in the same graphs. We propose to decouple explicit and implicit relationships among items. As such, we can capture the prior knowledge encapsulated in explicit dependencies and learned implicit correlations among items simultaneously in a flexible and more interpretable manner for effective recommendations. We design a dual graph neural network that leverages the feature representations extracted by two GNNs: a graph neural network with a single gate (SG-GNN) and an adaptive graph neural network (A-GNN). The former models explicit dependencies among items. The latter employs a self-learning strategy to capture implicit correlations among items. Our experiments on four real-world datasets show our model outperforms state-of-the-art methods by a large margin, achieving 18.46% and 70.72% improvement in [email protected], and 49.10% and 115.29% improvement in [email protected] on Diginetica and LastFM datasets.

Abstract Multivariate time series classification is a critical problem in data mining with broad applications. It requires harnessing the inter-relationship of multiple variables and various ranges of temporal dependencies to assign the correct classification label of the time series. Multivariate time series may come from a wide range of sources and be used in various scenarios, bringing the classifier challenge of temporal representation learning. We propose a novel convolutional neural network architecture called Attentional Gated Res2Net for multivariate time series classification. Our model uses hierarchical residual-like connections to achieve multi-scale receptive fields and capture multi-granular temporal information. The gating mechanism enables the model to consider the relations between the feature maps extracted by receptive fields of multiple sizes for information fusion. Further, we propose two types of attention modules, channel-wise attention and block-wise attention, to better leverage the multi-granular temporal patterns. Our experimental results on 14 benchmark multivariate time-series datasets show that our model outperforms several baselines and state-of-the-art methods by a large margin. Our model outperforms the SOTA by a large margin, the classification accuracy of our model is 10.16% better than the SOTA model. Besides, we demonstrate that our model improves the performance of existing models when used as a plugin. Further, based on our experiments and analysis, we provide practical advice on applying our model to a new problem.

Multivariate time series classification is a critical problem in data mining with broad applications. We design a novel convolutional neural network architecture, Attentional Gated Res2Net, for robust multivariate time series classification. AGRes2Net uses hierarchical residual-like connections to achieve multi-scale receptive fields and to capture multi- granular temporal patterns. It further employs the gated mechanism to harness inter-relationship between feature maps. We propose two types of attention modules, namely channel-wise attention and block-wise attention, to leverage the multi-granular temporal patterns. Our experiments on six benchmark datasets demonstrate that AGRes2Net not only outperforms several baselines and state-of-the-art methods but also improves the classification accuracy of existing models when used as a plug-in.

Multivariate time series analysis is an important problem in data mining because of its widespread applications. With the increase of time series data available for training, implementing deep neural networks in the field of time series analysis is becoming common. Res2Net, a recently proposed backbone, can further improve the state-of-the-art networks as it improves the multi-scale representation ability through connecting different groups of filters. However, Res2Net ignores the correlations of the feature maps and lacks the control on the information interaction process. To address that problem, in this paper, we propose a backbone convolutional neural network based on the thought of gated mechanism and Res2Net, namely Gated Res2Net (GRes2Net), for multivariate time series analysis. The hierarchical residual-like connections are influenced by gates whose values are calculated based on the original feature maps, the previous output feature maps and the next input feature maps thus considering the correlations between the feature maps more effectively. Through the utilization of gated mechanism, the network can control the process of information sending hence can better capture and utilize the both the temporal information and the correlations between the feature maps. We evaluate the GRes2Net on four multivariate time series datasets including two classification datasets and two forecasting datasets. The results demonstrate that GRes2Net have better performances over the state-of-the-art methods thus indicating the superiority.