To discover the condition of roads, a large number of detection algorithms have been proposed, most of which apply machine learning methods by time and frequency processing in acceleration and velocity data. However, few of them pay attention to the similarity of the data itself when the vehicle passes over the road anomalies. In this article, we propose a method to detect road anomalies by comparing the data windows with various length using Dynamic Time Warping(DTW) method. We propose a model to prove that the maximum acceleration of a vehicle passing through a road anomaly is linear with the height of the road barrier, and it's verified by an experiment. This finding suggests that it is reasonable to divide the window by threshold detection. We also apply a brief random forest filter to roughly distinguish normal windows from anomaly windows using the aforementioned theory, in order to reduce the time consumption. From our study, a system is proposed that utilizes a series of acceleration data to discover where might be anomalies on the road, named as Quick Filter Based Dynamic Time Warping (QFB-DTW). We show that our method performs clearly beyond some existing methods. To support this conclusion, experiments are conducted based on three data sets and the results are statistically analyzed. We expect to lay the first step to some new thoughts to the field of road anomalies detection in subsequent work.

Multimodal information extraction (MIE) gains significant attention as the popularity of multimedia content increases. However, current MIE methods often resort to using task-specific model structures, which results in limited generalizability across tasks and underutilizes shared knowledge across MIE tasks. To address these issues, we propose UMIE, a unified multimodal information extractor to unify three MIE tasks as a generation problem using instruction tuning, being able to effectively extract both textual and visual mentions. Extensive experiments show that our single UMIE outperforms various state-of-the-art (SoTA) methods across six MIE datasets on three tasks. Furthermore, in-depth analysis demonstrates UMIE's strong generalization in the zero-shot setting, robustness to instruction variants, and interpretability. Our research serves as an initial step towards a unified MIE model and initiates the exploration into both instruction tuning and large language models within the MIE domain. Our code, data, and model are available at https://github.com/ZUCC-AI/UMIE.

Road anomaly detection has attracting increasing attention in recent years due to its significant role in the public transportation of modern cities. A few methods has been proposed to detect road anomaly with inertial sensors (e.g., accelerometer and gyroscope), which usually utilize classification techniques by extracting time and frequency domain features from inertial sensor data. However, existing methods are time consuming since these methods perform on the whole datasets. In addition, few of them pay attention to the self-similarity of the data when vehicle passes over the road anomalies. In this paper, we propose QDetect, a road anomaly detection system with less data-dependency via querying and recomparing. Specifically, QDetect consists of two phases: 1) Query filter. This phase is designed to roughly extract road anomaly segments by matching existing labelled anomalies; 2) Re-comparison on suspicious anomalies to identify their anomaly types. We have conducted comprehensive experiments on two realworld data sets, and the results show that our method outperforms some existing methods in both detection performance and running time. We expect to lay the first step to some new thoughts to the field of real-time road anomalies detection in subsequent work.

An improved understanding of customer preference is crucial for successful business in physical stores. Online stores are capable learning customer preference from the click logs and transaction records, while retailers with physical store still lack effective methods to in-depth understand customer preference. Fortunately, user-generated data from mobile devices and social media are providing rich information to uncover customer preference. In this paper, we present a novel approach to mine customer preference in physical stores from their interaction behaviors. To demonstrate the utility of the proposed model, we conduct a store-type recommendation model for physical stores by jointly considering the learned customer preference and temporal influence. We have performed a comprehensive experiment evaluation on two real-world data sets, which are collected by more than 120 000 customers during 12 months from two urban shopping malls. Experimental results show the superiority of the proposed model not only in recommending interesting stores for customer, but also help retailers better understand customer preference.

Nested named entity recognition (NER) is a linguistic phenomenon that has received increasing attention in the NLP community. In this paper, we propose a novel joint learning network of the token context and span feature (TCSF) for nested NER. Our model is a combination of token context network (TCN) for token learning and deep residual convolutional neural network (CNN) and span relation network (SRN) for span learning. Span features are represented at both the token level and span relation level. The span relation representation of SRN is trained on the similarity of span features and positions by attention weights. The IoU metric is employed for span filtering and analysis of the overlapping adjacent spans. Moreover, we propose a novel head-inner-tail ( ${\rm {HI^{p}T}}$ ) operation to extend the inner features in spans for a fixed-length representation. TCSF is a fully end-to-end entity recognition model. We perform a set of comprehensive experiments, including an ablation study on the ACE and GENIA datasets, and show state-of-the-art performance without and with the pretrained language models.

Traffic flow forecasting is an important part of intelligent transportation systems. Accurate traffic flow forecasting can not only provide travel advice for people, but also improve traffic management efficiency. In this paper, we propose a novel traffic flow prediction model based on sparse regression, which can effectively and conveniently combine spatio-temporal factor. We analyze the traffic flow data, and design a multi-factor dictionary with spatio-temporal factor. Temporal factor and spatial factor are added to the multi-factor dictionary in the form of basis vectors which make the model easy to expand. The multi-factor coefficient solution based on LASSO guarantees the sparsity of the coefficients, which can quantitatively analyze the influence of spatio-temporal factor. Experimental results in urban and suburban scenarios indicate that the prediction accuracy is improved after adding the temporal factor and spatial factor, and traffic flow on urban roads is more susceptible to spatial factors. We compared our method with other models in three different prediction intervals, and the experimental results show that our method achieved the best prediction performance.