Existing multi-behavior recommendations tend to prioritize performance at the expense of explainability, while current explainable methods suffer from limited generalizability due to their reliance on external information. Neuro-Symbolic integration offers a promising avenue for explainability by combining neural networks with symbolic logic rule reasoning. Concurrently, we posit that user behavior chains (e.g., view->cart->buy) inherently embody an endogenous logic suitable for explicit reasoning. However, these observational multiple behaviors are plagued by confounders, causing models to learn spurious correlations. By incorporating causal inference into this Neuro-Symbolic framework, we propose a novel Causal Neuro-Symbolic Reasoning model for Explainable Multi-Behavior Recommendation (CNRE). CNRE operationalizes the endogenous logic by simulating a human-like decision-making process. Specifically, CNRE first employs hierarchical preference propagation to capture heterogeneous cross-behavior dependencies. Subsequently, it models the endogenous logic rule implicit in the user's behavior chain based on preference strength, and adaptively dispatches to the corresponding neural-logic reasoning path (e.g., conjunction, disjunction). This process generates an explainable causal mediator that approximates an ideal state isolated from confounding effects. Extensive experiments on three large-scale datasets demonstrate CNRE's significant superiority over state-of-the-art baselines, offering multi-level explainability from model design and decision process to recommendation results.

Understanding the spatiotemporal characteristics of criminal activities in a city, or urban crime dynamics for short, is essential for developing ways to control crime and improve urban safety. While much effort has been devoted to this field, most of the existing studies have led to overly generalized findings, obscuring the ways in which dynamic patterns of criminal activities vary by place, time, and situational context. To address this challenge, this article proposes a novel space-time-context-aware tensor decomposition framework, namelySTCTD-Crime, for an in-depth understanding of urban crime dynamics. Specifically,STCTD-Crimefirst constructs a third-order tensor to represent crime data, which provides an elegant way to model spatial, temporal, and contextual factors simultaneously. Then, it decouples the influence that the three factors exerts on criminal activities via the tensor decomposition, enabling the observation of the extent to which each factor affects crime incidents occurring at different regions, within different time slices, and under different situational contexts. Moreover,STCTD-Crimeexploits spatiotemporal correlations between criminal activities to facilitate the understanding of dynamics by seamlessly integrating a crime-number-guided correlation learning method into the framework. Finally, an alternating optimization based scheme is developed to solve the optimization problem, which results in an efficient urban crime dynamics discovery procedure. Extensive analyses on crime datasets drawn from real-world sources convincingly demonstrate the effectiveness ofSTCTD-Crime.

Crime prediction, which focuses on forecasting the occurrence of criminal activities across city regions before they occur, constitutes an essential capability of surveillance systems designed to enhance urban security. While much effort has been invested in this field, most of the existing studies pay little attention to the influence of situational contexts on criminal activities, which hinders further improvement in prediction performance. To address this challenge, we propose a novel context-aware Bayesian tensor decomposition framework, namely cBTD-Crime, for citywide multi-step crime prediction. More specifically, cBTD-Crime first constructs a third-order tensor to simultaneously model spatial, temporal, and contextual factors and then applies the CP decomposition to exploit the intricate relationships between the three factors to facilitate the prediction process. To reduce the parameter tuning cost, cBTD-Crime further reformulates the problem from a probabilistic perspective, where a range of carefully selected distributions are placed on the spatial, temporal, and contextual latent factors. Finally, an efficient Gibbs sampling procedure is developed to generate a series of samples and the arithmetic mean is computed to obtain the predicted number of crime incidents. Experimental results show that cBTD-Crime achieves superior performance on real-world crime datasets in terms of different evaluation metrics.

Multivariate time series anomaly detection has shown potential in various fields, such as finance, aerospace, and security. The fuzzy definition of data anomalies, the complexity of data patterns, and the scarcity of abnormal data samples pose significant challenges to anomaly detection. Researchers have extensively employed autoencoders (AEs) and generative adversarial networks (GANs) in studying time series anomaly detection methods. However, relying on reconstruction error, the AE-based anomaly detection algorithm needs more effective regularization methods, rendering it susceptible to the problem of overfitting. Meanwhile, GAN-based anomaly detection algorithms require high-quality training data, significantly impacting their practical deployment. We propose a novel GAN based on a dual-discriminator structure to address these issues. The model first processes the data with the generator to obtain the reconstruction error and then calculates pseudo-labels to divide the data into two categories. One data category is input into the first discriminator, where a minor loss between the data and its reconstructed counterpart is better. The other data category is input into the second discriminator, where a larger loss between the data and its reconstructed counterpart is better. Through this process, the model can effectively constrain the generator, retaining information on normal data during data reconstruction while discarding information on abnormal data. After conducting experiments on multiple benchmark datasets, the proposed GAN based on a dual-discriminator structure achieved good results in anomaly detection, outperforming several advanced methods. Additionally, the model also performed well in practical transformer data.

Tourism is an important industry and a popular leisure activity involving billions of tourists per annum. One challenging problem tourists face is identifying attractive Places-of-Interest (POIs) and planning the personalized trip with time constraints. Most of the existing trip recommendation methods mainly consider POI popularity and user preferences, and focus on the last visited POI when choosing the next POI. However, the visit patterns and their asymmetry property have not been fully exploited. To this end, in this article, we present a GRM-RTrip (short for G raph-based R epresentation M ethod for R einforce Trip Recommendation) framework. GRM-RTrip learns POI representations from incoming and outgoing views to obtain asymmetric POI-POI transition probability via POI-POI graph networks, and then fuses the trained POI representation into a user-POI graph network to estimate user preferences. Finally, after formulating the personalized trip recommendation as a Markov Decision Process (MDP), we utilize a reinforcement learning algorithm for generating a personalized trip with maximal user travel experience. Extensive experiments are performed on the public datasets and the results demonstrate the superiority of GRM-RTrip compared with the state-of-the-art trip recommendation methods.

This paper explores human activities recognition from sensor-based multi-dimensional streams. Recently, deep learning-based methods such as LSTM and CNN have achieved important progress in practical application scenarios. However, in most previous deep learning-based methods exist potential challenges such as class imbalance and multi-modal heterogeneity with time and sensor signals. To handle those problems, we propose a graph LSTM and Metric Learning model (GLML) with multiple construction graph fusion by modeling the sensor-aspect signals and the graph-aspect activities. GLML is a semi-supervised co-training architecture, which can be seen as several iteratively pseudo-labels sampling processing in the unlabeled data. Specifically, we construct three graphs to capture the different relations in each timestamp. Meanwhile, the graph attention model and attention mechanism are proposed to integrate multiple graph interactions for different sensor signals. Furthermore, to obtain a fixed representation of hidden state units and their neighboring nodes, we introduce the Graph LSTM to learn the graph-aspect relations from graph-structured constructed graphs. Notably, we propose a multi-task classification model combining loss function for classification distribution with deep metric learning to enhance the representation ability of the multi-modal sensor data. Experimental results on three public datasets demonstrate that our proposed GLML model has at least 2.44% improved in average against the state-of-the-art methods.

Predicting grain losses and waste rate (LWR) is critical for agricultural planning and grain policy development. Capturing the stage interaction and generating robust features are the main challenges in grain LWR prediction. In this article, we propose MTGA, a Multitask Gated recurrent unit (GRU) Autoencoder, approach to 1) obtain the robust feature representation for the prediction task and 2) explore the time-ordered interactions among different stages of the grain chain. Specifically, we design multiple GRU encoder-decoder pairs to co-reconstruct the stage features in a common space for robust feature learning. Then, an attention mechanism is proposed better to fuse the reconstructed features from the GRU encoder-decoder pairs. Furthermore, we utilize the multitask for reconstructed loss and grain LWR prediction. We introduce the reconstructed loss task as an auxiliary task to help us to represent the robust features. Besides, we introduce the LWR prediction as main task to learn the parameters for prediction task. We collected the data with questionnaires, interviews, or data from grain management institutes for experiments. The evaluation results show that grain LWR prediction by our approach achieves the best results compared to several state-of-the-art prediction models. Moreover, our method gains overall performance decline of 12.5-18.3% on mean absolute error and root mean square error metrics.

Hospital re-admission refers to special medical events that a patient previously discharged from the hospital is readmitted within a short period of time (say 30 days). A re-admission not only downgrades the quality of living of the patient, it also adds significant financial burdens to the health care systems. To date, many systems exist to use computational approaches to predict the likelihood of a patient being readmitted in the future for medical decision assistance. When building predictive models for hospital re-admission prediction, one essential challenge is that sample distributions in the data are severely imbalanced where, typically, less than 10% of patients are likely going to be readmitted in a near future. A predictive model, without considering sample imbalance, will unlikely generate accurate results for prediction. To date, no existing re-admission model has explicitly addressed such data imbalance issues in their systems. In this paper, we consider hospital re-admission prediction with imbalanced sample distributions, and propose to use localized sampling approach to help build accurate predictive models. For localized sampling, we emphasize on samples which are difficult to classify, and allow the sampling process to bias to such instances. Because finding instances difficult to classify requires calculation of distance between instances, and the high dimensionality of Electronic Health Records (EHR) data makes the distance calculation highly ineffective, we propose to use latent topic embedding to reduce the sample from high dimensionality to a handful of low dimensional topic space for effective and accurate calculation of the distance between instances. By using localized sampling to build multiple versions of balanced datasets, we are able to train multiple predictive models and combine their results for prediction. Experiments and comparisons on data collected from several South Florida regional hospitals demonstrate the performance of our method.