Large language models (LLMs) are revolutionizing user interactions in online map applications by enabling conversational interfaces with intelligent map agents. However, inherent ambiguities and nuances in human communication often lead to incomplete or unclear user instructions. While generating clarification questions can mitigate this issue, existing methods—which rely on prompt-based LLM assessments or supervised fine-tuning (SFT) of LLMs with limited annotated data—struggle to reliably determine when clarification is necessary, resulting in cold-start issues and reduced adaptability. To address this gap, we propose an uncertainty-aware dynamic planning framework for intent disambiguation in interactive agent systems, exemplified by Baidu Maps. Our framework leverages LLMs to dynamically generate agent action sequences while estimating query uncertainty. When uncertainty thresholds are exceeded, targeted clarification questions are triggered. Besides, to efficiently navigate the vast uncertainty space, we introduce a novel beam search-based pruning strategy. Crucially, the framework supports context-aware task planning without any additional model training. We evaluate our approach on Baidu Maps and a public robotic task, focusing on uncertainty management and adaptability. Experiments demonstrate that the framework achieves high precision across diverse LLMs without requiring an additional training phase, highlighting its versatility and robustness. Ablation studies confirm that the framework can significantly improve user intent recognition and task success rates.

In modern cities, there is an increasing trend for the development of business agglomeration, which can foster the prosperity of individual businesses by clustering stores and industries. Recently, the advent of Point-of-Interest (POI) data enables a new paradigm for studying the causal effect of business agglomeration in a data-driven way. To this end, we aim to quantify the contribution of the agglomeration effect to the check-in volume at POIs. This is a non-trivial causal effect estimation task due to the higher-order spatial interference typically exhibited by the agglomeration distribution. Moreover, the confounding bias can be exacerbated due to the complex spatial and functional properties inherent to confounders. Therefore, we propose a Causal effect estimation framework for AgglomeRation Effect (CARE) measurement, which includes a Spatial Interference Diffusion Network (SIDN) and a Disentangled Propensity Estimator (DPE) . SIDN captures spatial interference by spreading the treatment effect among POIs through a dedicated spatial agglomeration hypergraph. Then, DPE models a POI’s propensity of receiving the treatment and further unravels the spatial and inherent aspects of propensity by disentangled learning objectives. In addition, we incorporate SIDN and DPE into a unified causal effect estimation architecture using neural Robinson decomposition. Finally, extensive experiments on three real-world datasets validate the effectiveness and universality of CARE for measuring the agglomeration effect.

Urban land use, intrinsically linked to people’s daily activities, undergoes continuous evolution, presenting a complex interplay that remains partially understood. To bridge this gap, our study leverages fine-grained human mobility data to predict these changes, adopting a novel approach that conceptualizes “community-level” land use shifts as a regression problem and represents citywide changes through dynamic graphs. We harness recent advancements in graph neural networks (GNNs), which, despite their success in various applications, face challenges in directly predicting land use changes due to the temporal mismatch between the slow evolution of urban land and the immediacy of human mobility data. Our research stands out by introducing a temporal skeleton for dynamic GNNs to synchronize human activity graphs with urban land use changes, a dynamic heterogeneous GNN approach for integrating diverse human activity data to capture essential temporal dependencies, and a novel algorithm powered by causal inference to elucidate the primary factors influencing land use predictions at the community level, all of which contribute to a training process informed by the generated causal graph. Empirically validated on three real-world datasets, our model demonstrates a performance leap over state-of-the-art baselines, marking a pivotal step toward understanding and predicting the dynamics of urban land use.

Origin-destination (OD) crowd flow, if more accurately inferred at a fine-grained level, has the potential to enhance the efficacy of various urban applications. While in practice for mining OD crowd flow with effect, the problem of spatially interpolating OD crowd flow occurs since the ineluctable missing values. This problem is further complicated by the inherent scarcity and noise nature of OD crowd flow data. In this paper, we propose an uncertainty-aware interpolative and explainable framework, namely UApex, for realizing reliable and trustworthy OD crowd flow interpolation. Specifically, we first design a Variational Multi-modal Recurrent Graph Auto-Encoder (VMR-GAE) for uncertainty-aware OD crowd flow interpolation. A key idea here is to formulate the problem as semi-supervised learning on directed graphs. Next, to mitigate the data scarcity, we incorporate a distribution alignment mechanism that can introduce supplementary modals into variational inference. Then, a dedicated decoder with a Poisson prior is proposed for OD crowd flow interpolation. Moreover, to make VMR-GAE more trustworthy, we develop an efficient and uncertainty-aware explainer that can provide explanations from the spatiotemporal topology perspective via the Shapley value. Extensive experiments on two real-world datasets validate that VMR-GAE outperforms the state-of-the-art baselines. Also, an exploratory empirical study shows that the proposed explainer can generate meaningful spatiotemporal explanations.

Recent trends in next-item recommendation systems have focused on modeling user intents. Traditional methods often extract users' inherent intents from the most representative items in a session, overlooking “unexpected items” that deviate from the majority in various contextual aspects. These unexpected items, frequently present, can be crucial indicators of a user's inclination towards exploring new options, signaling emerging intents that warrant significant attention. In response, we introduce DbMei, a novel approach that decouples user behaviors and emphasizes the modeling of emerging intents. DbMei distinguishes between two user behavior types: “focused shopping”, which aligns with users' inherent intents, and”wandering shopping”, which aligns with emerging intents. Focused shopping is analyzed using topic modeling and hypergraph learning while wandering shopping is explored through session neighbor retrieval. An exploitation-exploration mechanism is employed to determine the behavioral probability distribution for upcoming items. This integrated modeling of focused and wandering shopping behaviors drives our recommendation process. Extensive empirical studies on two real-world datasets, Amazon-KDD and Beauty, showcase DbMei's superiority over leading methods regarding Recall and MRR metrics. Our code is publicly available at https://github.com/sunlingdan-123/DbMei.

Human motion intentions are commonly identified from signals collected by sensors. However, these signals are susceptible to various noises and uncertainties, leading to unreliable identification accuracy. To enhance robustness and reliability, this study proposes a probabilistic fuzzy classifier for motion intent recognition in the presence of noise. The method begins by analyzing and estimating the stochastic effect of disturbances on the kernel parameter and regularization parameter. Subsequently, a new objective function is formulated, incorporating the distribution of these parameters. To solve this objective function, a probabilistic inference strategy is developed to estimate the distribution. Using this distribution information, a solving strategy for the fuzzy model is devised. By constructing the distribution relationship between disturbances and model parameters and incorporating probabilistic information in the model, the proposed method demonstrates enhanced robustness and reliability for motion intention recognition under noisy conditions. Experimental results validate that the proposed algorithm improves accuracy and robustness for motion intention recognition and outperforms other state-of-the-art recognition algorithms in noise environments.

Point-of-Interest (POI) recommendation, an important research hotspot in the field of urban computing, plays a crucial role in urban construction. While understanding the process of users’ travel decisions and exploring the causality of POI choosing is not easy due to the complex and diverse influencing factors in urban travel scenarios. Moreover, the spurious explanations caused by severe data sparsity, i.e., misrepresenting universal relevance as causality, may also hinder us from understanding users’ travel decisions. To this end, in this article, we propose a factor-level causal explanation generation framework based on counterfactual data augmentation for user travel decisions, named Factor-level Causal Explanation for User Travel Decisions (FCE-UTD), which can distinguish between true and false causal factors and generate true causal explanations. Specifically, we first assume that a user decision is composed of a set of several different factors. Then, by preserving the user decision structure with a joint counterfactual contrastive learning paradigm, we learn the representation of factors and detect the relevant factors. Next, we further identify true causal factors by constructing counterfactual decisions with a counterfactual representation generator, in particular, it can not only augment the dataset and mitigate the sparsity but also contribute to clarifying the causal factors from other false causal factors that may cause spurious explanations. Besides, a causal dependency learner is proposed to identify causal factors for each decision by learning causal dependency scores. Extensive experiments conducted on three real-world datasets demonstrate the superiority of our approach in terms of check-in rate, fidelity, and downstream tasks under different behavior scenarios. The extra case studies also demonstrate the ability of FCE-UTD to generate causal explanations in POI choosing.

Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high prediction capacity because of the high computational self-attention mechanism. Though one could lower the complexity of Transformers by inducing the sparsity in point-wise self-attentions for LTTF, the limited information utilization prohibits the model from exploring the complex dependencies comprehensively. To this end, we propose an efficient Transformer-based model, named Conformer, which differentiates itself from existing methods for LTTF in three aspects: (i) an encoder-decoder architecture incorporating a linear complexity without sacrificing information utilization is proposed on top of sliding-window attention and Stationary and Instant Recurrent Network (SIRN); (ii) a module derived from the normalizing flow is devised to further improve the information utilization by inferring the outputs with the latent variables in SIRN directly; (iii) the inter-series correlation and temporal dynamics in time-series data are modeled explicitly to fuel the downstream self-attention mechanism. Extensive experiments on seven real-world datasets demonstrate that Conformer outperforms the state-of-the-art methods on LTTF and generates reliable prediction results with uncertainty quantification.

Long-term urban crowd flow prediction involving the evolution trends of crowd flow is of great importance of traffic management, public safety and urban planning. However, learning long-term crowd flow is very challenging due to the latent effect of varied urban Point-of-Interests distribution, which is quite different from the short-term crowd flow mainly influenced by readily available external factors like weather, date, etc. The key issue for us is how to learn the interaction between POI distribution and human mobility in a dynamic way. To address this problem, we propose a POI-flow interaction based spatial-temporal framework (PFIST) for long-term crowd flow prediction. First, we model the long-term evolution representations of crowd flow and POI distribution. Then we study the dynamic interaction between POI transition patterns and crowd flow variation on different POI periods and categories. Afterwards, we decompose the flow sequence into long-term trend and daily variation parts and apply the normalized POI-flow interaction attention to the long-term trend parts. Finally, we model the spatial and multi-scale temporal dependencies to predict long-term crowd flow. Extensive experiments on Beijing map query track dataset and NYC taxi dataset demonstrate the superiority of PFIST.

Medical tests are crucial for treatment decision making. However, over-testing can often occur in any medical speciality or level of expertise. Since over-testing usually results in a financial burden for patients and is also a waste of medical resources, this naturally leads to the question: which medical test items (MTIs) are necessary and should be prioritized for the target patients? It is a nontrivial task to identify the right MTIs due to the diversified health status of patients and the complicated prerequisites of therapies. To this end, in this paper, we propose a data-driven approach to evaluate the priority which should be given to MTIs by modeling the relationships between MTIs and therapies. Specifically, we first develop a dual hierarchical topic model (DHTM), which views the adopted hierarchical therapies as labeled topics and the MTI reports, i.e., the set of hierarchical attribute-value pairs (AVPs), as documents. Then, with the therapy-AVP distribution and the partial MTI reports of the target patient, we can scope the candidate therapies, which are further utilized to evaluate the accumulated gain of MTIs to be tested. Moreover, the next MTI recommendation is conducted based on the gains. Finally, extensive experiments on real-world medical data validate the effectiveness of our approach, and some interesting observations are also provided. The code is available at https://github.com/mtirec/MtiRec.

Recent advances in graph representation learning provide new opportunities for computational drug-target interaction (DTI) prediction. However, it still suffers from deficiencies of dependence on manual labels and vulnerability to attacks. Inspired by the success of self-supervised learning (SSL) algorithms, which can leverage input data itself as supervision,we propose SupDTI, a SSL-enhanced drug-target interaction prediction framework based on a heterogeneous network (i.e., drug-protein, drug-drug, and protein-protein interaction network; drug-disease, drug-side-effect, and protein-disease association network; drug-structure and protein-sequence similarity network). Specifically, SupDTI is an end-to-end learning framework consisting of five components. First, localized and globalized graph convolutions are designed to capture the nodes' information from both local and global perspectives, respectively. Then, we develop a variational autoencoder to constrain the nodes' representation to have desired statistical characteristics. Finally, a unified self-supervised learning strategy is leveraged to enhance the nodes' representation, namely, a contrastive learning module is employed to enable the nodes' representation to fit the graph-level representation, followed by a generative learning module which further maximizes the node-level agreement across the global and local views by learning the probabilistic connectivity distribution of the original heterogeneous network. Experimental results show that our model can achieve better prediction performance than state-of-the-art methods.

In order to address the flexible requirements on load, flight speed, and maneuverability in actual flight conditions, a hand-launched fixed-wing unmanned aerial vehicle (UAV) is designed with high performance in portability, lightweight, and maneuverability. On this basis, a novel system-decomposition-based robust control method is proposed to achieve a satisfactory control performance for this designed UAV under internal/external uncertainties. First, considering the feature that the coupling terms are usually small in most flight conditions and may be regarded as disturbance, the complex flight system is decomposed into a group of simple subsystems with disturbance, namely, roll–yaw subsystem, pitch–altitude subsystem, and airspeed subsystem. Since the complexity of each subsystem is much smaller than the original system, this will reduce the difficulty of the controller design and complexity of the controller. Besides, to improve the tracking performance and robustness to disturbances, an extended state observer based robust control method is proposed for each subsystem. The stability and robustness of the proposed control method are effectively demonstrated by the theoretical analysis and the actual flight experiments on the designed UAV.

Although remarkable progress on the neural table-to-text methods has been made, the generalization issues hinder the applicability of these models due to the limited source tables.Large-scale pretrained language models sound like a promising solution to tackle such issues.However, how to effectively bridge the gap between the structured table and the text input by fully leveraging table information to fuel the pretrained model is still not well explored.Besides, another challenge of integrating the deliberation mechanism into the textto-text pretrained model for solving the tableto-text task remains seldom studied.In this paper, to implement the table-to-text generation with pretrained language model, we propose a table structure understanding and text deliberating approach, namely TASD.To be specific, we devise a three-layered multi-head attention network to realize the table-structureaware text generation model with the help of the pretrained language model.Furthermore, a multi-pass decoder framework is adopted to enhance the capability of polishing generated text for table descriptions.The empirical studies, as well as human evaluation, on two public datasets, validate that our approach can generate faithful and fluent descriptive texts for different types of tables.

As a promising learning paradigm for addressing the data scarcity and distribution mismatch issues, cross-domain prediction aims to leverage the transferable knowledge from the source domain to solve the learning problems in the target domain. Indeed, many urban computing tasks, such as cross- city/mode traffic flow prediction, have to face the severe data scarcity problem due to the heterogeneity in different data sources as well as the imbalanced development among cities. To this end, in this paper, we propose a cross-domain learning framework, namely CCMHC, which exploits Hierarchical Correlation between domains for Cross-City cross-Mode traffic flow prediction. Specifically, we first measure the correlation among inter-city traffic flows by exploring the similarity of region functions and road-networks. In this step, we filter out the regions with lower transfer ability from the source city to the target city. Then, we calculate the temporal correlations of traffic flows across different modes to select a source region that is highly related to the target region in a dynamic way. Moreover, a cross-domain urban flow prediction method is devised by transferring shared knowledge from the source city to the target city. Finally, experimental results on real-world data demonstrate the superiority of CCMHC over the state-of-the-art transfer learning methods. In addition, the generalization ability of the CCMHC framework on different neural network-based models is also validated.

Time series forecasting has been a widely explored task of great importance in many applications. However, it is common that real-world time series data are recorded in a short time period, which results in a big gap between the deep model and the limited and noisy time series. In this work, we propose to address the time series forecasting problem with generative modeling and propose a bidirectional variational auto-encoder (BVAE) equipped with diffusion, denoise, and disentanglement, namely D3VAE. Specifically, a coupled diffusion probabilistic model is proposed to augment the time series data without increasing the aleatoric uncertainty and implement a more tractable inference process with BVAE. To ensure the generated series move toward the true target, we further propose to adapt and integrate the multiscale denoising score matching into the diffusion process for time series forecasting. In addition, to enhance the interpretability and stability of the prediction, we treat the latent variable in a multivariate manner and disentangle them on top of minimizing total correlation. Extensive experiments on synthetic and real-world data show that D3VAE outperforms competitive algorithms with remarkable margins. Our implementation is available at https://github.com/PaddlePaddle/PaddleSpatial/tree/main/research/D3VAE.

Pre-travel out-of-town recommendation aims to recommend Point-of-Interests (POIs) to the users who plan to travel out of their hometown in the near future yet have not decided where to go, i.e., their destination regions and POIs both remain unknown. It is a non-trivial task since the searching space is vast, which may lead to distinct travel experiences in different out-of-town regions and eventually confuse decision-making. Besides, users' out-of-town travel behaviors are affected not only by their personalized preferences but heavily by others' travel behaviors. To this end, we propose a Crowd-Aware Pre-Travel Out-of-town Recommendation framework (CAPTOR) consisting of two major modules: spatial-affined conditional random field (SA-CRF) and crowd behavior memory network (CBMN). Specifically, SA-CRF captures the spatial affinity among POIs while preserving the inherent information of POIs. Then, CBMN is proposed to maintain the crowd travel behaviors w.r.t. each region through three affiliated blocks reading and writing the memory adaptively. We devise the elaborated metric space with a dynamic mapping mechanism, where the users and POIs are distinguishable both inherently and geographically. Extensive experiments on two real-world nationwide datasets validate the effectiveness of CAPTOR against the pre-travel out-of-town recommendation task.

The least-square support vector machine (LS-SVM) has been deeply studied in the machine-learning field and widely applied on a great deal of occasions. A disadvantage is that it is less efficient in dealing with the non-Gaussian noise. In this article, a novel probabilistic LS-SVM is proposed to enhance the modeling reliability even data contaminated by the non-Gaussian noise. The stochastic effect of noise on the kernel function and the regularization parameter is first analyzed and estimated. On the basis of this, a new objective function is constructed under a probabilistic sense. A probabilistic inference method is then developed to construct the distribution of the model parameter, including distribution estimation of both the kernel function and the regularization parameter from data. Using this distribution information, a solving strategy is then developed for this new objective function. Different from the original LS-SVM that uses a deterministic scenario approach to gain the model, the proposed method builds the distribution relation between the model and noise and makes use of this distribution information in the process of modeling; thus, it is more robust for modeling of noise data. The effectiveness of the proposed probabilistic LS-SVM is demonstrated by using both artificial and real cases.

Recent years have witnessed the rapid development of car-hailing services, which provide a convenient approach for connecting passengers and local drivers using their personal vehicles. At the same time, the concern on passenger safety has gradually emerged and attracted more and more attention. While car-hailing service providers have made considerable efforts on developing real-time trajectory tracking systems and alarm mechanisms, most of them only focus on providing rescue-supporting information rather than preventing potential crimes. Recently, the newly available large-scale car-hailing order data have provided an unparalleled chance for researchers to explore the risky travel area and behavior of car-hailing services, which can be used for building an intelligent crime early warning system. To this end, in this article, we propose a Risky Area and Risky Behavior Evaluation System (RARBEs) based on the real-world car-hailing order data. In RARBEs, we first mine massive multi-source urban data and train an effective area risk prediction model, which estimates area risk at the urban block level. Then, we propose a transverse and longitudinal double detection method, which estimates behavior risk based on two aspects, including fraud trajectory recognition and fraud patterns mining. In particular, we creatively propose a bipartite graph-based algorithm to model the implicit relationship between areas and behaviors, which collaboratively adjusts area risk and behavior risk estimation based on random walk regularization. Finally, extensive experiments on multi-source real-world urban data clearly validate the effectiveness and efficiency of our system.

The understanding of people’s inter-regional mobility behaviors, such as predicting the next activity region (AR) or uncovering the intentions for regional mobility, is of great value to public administration or business interests. While there are numerous studies on human mobility, these studies are mainly from a statistical view or study movement behaviors within a region. The work on individual-level inter-regional mobility behavior is limited. To this end, in this article, we propose a dynamic region-relation-aware graph neural network (DRRGNN) for exploring individual mobility behaviors over ARs. Specifically, we aim at developing models that can answer three questions: (1) Which regions are the ARs? (2) Which region will be the next AR, and (3) Why do people make this regional mobility? To achieve these tasks, we first propose a method to find out people’s ARs. Then, the designed model integrates a dynamic graph convolution network (DGCN) and a recurrent neural network (RNN) to depict the evolution of relations between ARs and mine the regional mobility patterns. In the learning process, the model further considers peoples’ profiles and visited point-of-interest (POIs). Finally, extensive experiments on two real-world datasets show that the proposed model can significantly improve accuracy for both the next AR prediction and mobility intention prediction.

Transportation recommendation is one important map service in navigation applications. Previous transportation recommendation solutions fail to deliver satisfactory user experience because their recommendations only consider routes in one transportation mode (uni-modal, e.g., taxi, bus, cycle) and largely overlook situational context. In this work, we propose$\mathsf {Hydra}$, a multi-task deep learning based recommendation system that offers multi-modal transportation planning and is adaptive to various situational context (e.g., nearby point-of-interest (POI) distribution and weather). We leverage the availability of existing routing engines and big urban data, and design a novel two-level framework that integrates uni-modal and multi-modal (e.g., taxi-bus, bus-cycle) routes as well as heterogeneous urban data for intelligent multi-modal transportation recommendation. In addition to urban context features constructed from multi-source urban data, we learn the latent representations of users, origin-destination (OD) pairs and transportation modes based on user implicit feedbacks, which captures the collaborative transportation mode preferences of users and OD pairs. Moreover, we propose two models to recommend the proper route among various uni-modal and multi-modal transportation routes: (1) a light-weight gradient boosting decision tree (GBDT) based recommendation model; and (2) a multi-task wide and deep learning (MTWDL) based recommendation model. We also optimize the framework to support real-time, large-scale route query and recommendation. We deploy$\mathsf {Hydra}$on Baidu Maps,11.https://maps.baidu.com/.one of the world's largest map services. Real-world urban-scale experiments demonstrate the effectiveness and efficiency of our proposed system. Since its deployment in August 2018,$\mathsf {Hydra}$has answered over a hundred million route recommendation queries made by over ten million distinct users. The GBDT based model and MTWDL based model achieve 82.8 and 96.6 percent relative improvement of user click ratio, respectively.

Understanding human mobility patterns at the point-of-interest (POI) scale plays an important role in enhancing business intelligence in mobile environments. While large efforts have been made in this direction, most studies simply utilize POI check-ins to mine the concerned mobility patterns, the effectiveness of which is usually hindered due to data sparsity. To obtain better POI-based human mobility for mining, in this paper, we strive to directly annotate the POIs associated with raw user-generated mobility records. We propose a neural context fusion approach which integrates various context factors in people's POI-visiting behaviors. Our approach evaluates the preference and transition factors via representation learning. Notably, we incorporate an attention mechanism to deal with the randomized transitions in raw mobility. The domain knowledge factors, i.e., distance, time and popularity, remain effective and our approach further includes them from a data-driven perspective. Factors are automatically fused with a feed-forward neural network. Furthermore, we exploit a multi-head architecture to enhance the model expressiveness. Using two real-life data sets, we conduct our experimental study and find that our approach consistently outperforms the state-of-the-art baselines by at least 32 percent in accuracy. Besides, we demonstrate the utility of the obtained POI-based human mobility with a POI recommendation example.

A session-based recommender system (SBRS) captures users’ evolving behaviors and recommends the next item by profiling users in terms of items in a session. User intent and user preference are two factors affecting his (her) decisions. Specifically, the former narrows the selection scope to some item types, while the latter helps to compare items of the same type. Most SBRSs assume one arbitrary user intent dominates a session when making a recommendation. However, this oversimplifies the reality that a session may involve multiple types of items conforming to different intents. In current SBRSs, items conforming to different user intents have cross-interference in profiling users for whom only one user intent is considered. Explicitly identifying and differentiating items conforming to various user intents can address this issue and model rich contextual information of a session. To this end, we design a framework modeling user intent and preference explicitly, which empowers the two factors to play their distinctive roles. Accordingly, we propose a key-array memory network (KA-MemNN) with a hierarchical intent tree to model coarse-to-fine user intents. The two-layer weighting unit (TLWU) in KA-MemNN detects user intents and generates intent-specific user profiles. Furthermore, the hierarchical semantic component (HSC) integrates multiple sets of intent-specific user profiles along with different user intent distributions to model a multi-intent user profile. The experimental results on real-world datasets demonstrate the superiority of KA-MemNN over selected state-of-the-art methods.

Transportation demand prediction is of great importance to urban governance and has become an essential function in many online applications. While many efforts have been made for regional transportation demand prediction, predicting the diversified transportation demand for different communities (e.g., the aged, the juveniles) remains an unexplored problem. However, this task is challenging because of the joint influence of spatio-temporal correlation among regions and implicit correlation among different communities. To this end, in this paper, we propose the Multi-task Spatio-Temporal Network with Mutually-supervised Adaptive task grouping (Ada-MSTNet) for community-aware transportation demand prediction. Specifically, we first construct a sequence of multi-view graphs from both spatial and community perspectives, and devise a spatio-temporal neural network to simultaneously capture the sophisticated correlations between regions and communities, respectively. Then, we propose an adaptively clustered multi-task learning module, where the prediction of each region-community specific transportation demand is regarded as distinct task. Moreover, a mutually supervised adaptive task grouping strategy is introduced to softly cluster each task into different task groups, by leveraging the supervision signal from one another graph view. In such a way, Ada-MSTNet is not only able to share common knowledge among highly related communities and regions, but also shield the noise from unrelated tasks in an end-to-end fashion. Finally, extensive experiments on two real-world datasets demonstrate the effectiveness of our approach compared with seven baselines.

Out-of-town recommendation is designed for those users who leave their home-town areas and visit the areas they have never been to before. It is challenging to recommend Point-of-Interests (POIs) for out-of-town users since the out-of-town check-in behavior is determined by not only the user’s home-town preference but also the user’s travel intention. Besides, the user’s travel intentions are complex and dynamic, which leads to big difficulties in understanding such intentions precisely. In this paper, we propose a TRAvel-INtention-aware Out-of-town Recommendation framework, named TRAINOR. The proposed TRAINOR framework distinguishes itself from existing out-of-town recommenders in three aspects. First, graph neural networks are explored to represent users’ home-town check-in preference and geographical constraints in out-of-town check-in behaviors. Second, a user-specific travel intention is formulated as an aggregation combining home-town preference and generic travel intention together, where the generic travel intention is regarded as a mixture of inherent intentions that can be learned by Neural Topic Model (NTM). Third, a non-linear mapping function, as well as a matrix factorization method, are employed to transfer users’ home-town preference and estimate out-of-town POI’s representation, respectively. Extensive experiments on real-world data sets validate the effectiveness of the TRAINOR framework. Moreover, the learned travel intention can deliver meaningful explanations for understanding a user’s travel purposes.

Potential crowd flow prediction for new planned transportation sites is a fundamental task for urban planners and administrators. Intuitively, the potential crowd flow of the new coming site can be implied by exploring the nearby sites. However, the transportation modes of nearby sites (e.g. bus stations, bicycle stations) might be different from the target site (e.g. subway station), which results in severe data scarcity issues. To this end, we propose a data-driven approach, named MOHER, to predict the potential crowd flow in a certain mode for a new planned site. Specifically, we first identify the neighbor regions of the target site by examining the geographical proximity as well as the urban function similarity. Then, to aggregate these heterogeneous relations, we devise a cross-mode relational GCN, a novel relation-specific transformation model, which can learn not only the correlation but also the differences between different transportation modes. Afterward, we design an aggregator for inductive potential flow representation. Finally, an LTSM module is used for sequential flow prediction. Extensive experiments on real-world data sets demonstrate the superiority of the MOHER framework compared with the state-of-the-art algorithms.

Graph Neural Networks (GNNs) are prone to adversarial attacks and discriminatory biases. The cutting-edge studies usually adopt a perturbation-invariant consistency regularization strategy without considering the inherent prediction uncertainties, which can lead to unsatisfactory overconfidence for incorrect prediction under intent graph topology or node features attacks. Besides, operating on the complete graph structure is biased towards global level graph noise and brings severe computational issues. In this work, we develop a multi-view confidence-calibrated framework, called MCCNIFTY, for unified fair and stable graph representation learning. At its core is a multi-view uncertainty-aware node embedding learning module derived from evidential theory, including an intra-view evidence calibration, an inter-view evidence fusion, and an uncertainty-aware message passing process in a GNN architecture, which simultaneously optimizes for counterfactual fairness and stability at the sub-graph level. Experimental results on three real-world datasets demonstrate that our method is capable of adequately capturing inherent uncertainties while improving the fairness and stability via subgraph-induced multiview confidence calibration.

Neural network (NN) has been widely used in the field of modeling of lumped parameter systems. However, an NN approach cannot be used to model complex nonlinear distributed parameter systems (DPSs) because it does not account for this type of system's relationship with space. In this article, we propose a novel spatiotemporal NN (SNN) method to model nonlinear DPSs, which considers not only nonlinear dynamics regarding time, but also a nonlinear relationship with space. A temporal NN model was first constructed to represent the nonlinear temporal dynamics of each sensor's position. A spatial distribution function was then developed to represent the nonlinear relationship between spatial points. This strategy results in inherent consideration of any spatial dynamics. Finally, by integrating both the temporal NN model and the spatial distribution function, a novel SNN model was created to represent the spatiotemporal dynamics of the nonlinear DPSs. A two-step solving approach was further developed to learn the model. Additional analysis and proof of concept showed the effectiveness of this proposed method. This proposed method is different from traditional data-driven modeling methods in that it uses full information from all sensors and does not require model reduction technology. Case studies not only demonstrate the effectiveness of this proposed method, but also its superior modeling performance as compared with several commonly used methods.

Modeling distributed parameter systems (DPSs) are usually challenging due to their infinite dimension nature and strong nonlinearity. As a result, the commonly used DPS modeling methods often do not represent this kind of DPSs well due to model reduction and its neglect of nonlinear dynamics. Here, a novel spatiotemporal recurrent neural network (SRNN) modeling method was proposed for nonlinear DPSs. Generally, the space neighboring the points in a DPS interact each other by means of energy transfer, also known as spatial dynamics. In this SRNN model, its hidden layer at each time is designed to represent the spatial dynamics using a bidirectional RNN (BRNN). The BRNN has the ability to represent this complex interaction since its neighboring hidden layers are used to represent these adjacent spatial points and using a forward step and a backward step represents the interaction between neighboring hidden layers. Then, with the combination of all hidden layers of the SRNN over time, the temporal dynamics of the snapshots is exhibited and represented. In this way, this SRNN integrates the spatial/temporal dynamics together and is without requirement of model reduction. A solving approach is then proposed to find its solution, and a convergence analysis further proves that the proposed method can effectively reconstruct the nonlinear spatiotemporal dynamics of the nonlinear DPS. The article not only demonstrate the effectiveness of the proposed method, but also demonstrate its superior modeling performance as compared to several common methods.

Recent advances in graph representation learning provide new opportunities for computational drug-target interaction (DTI) prediction. Inspired by the emerging graph mutual information-based algorithms, we propose MMIDTI, a multi-level mutual information-aware DTI prediction framework based on a heterogeneous network (i.e., drug-protein, drug-drug and protein-protein interaction network; drug-disease, drug-side-effect, and protein-disease association network; drug-structure and protein-sequence similarity network). More specifically, MMIDTI leverages an encoder-decoder framework that can learn the type-aware and meta-path augmented node representations by following a contrastive learning paradigm. The encoder part is a Graph Convolutional Network (GCN) and the decoder is an inner product of the learned representations to recover the original heterogeneous network. Meanwhile, MMIDTI exploits two levels of mutual information: (1) maximizing local mutual information, to obtain node representations that capture the global information content of the entire heterogeneous graph. (2) maximizing the global mutual information, to constrain the node representation to have desired statistical characteristics. Experimental results show that our model can achieve better prediction performance than state-of-the-art methods.

Partial correlation-based connectivity networks can describe the direct connectivity between features while avoiding spurious effects, and hence they can be implemented in diagnosing complex dynamic multivariate systems. However, existing studies mainly focus on single systems that are ill-equipped for incremental learning. Moreover, related methods estimate temporal connectivity network by imposing only sparse regularization without integrating pattern priors (e.g., inter-system shared pattern and intra-system intrinsic pattern), which have been proven effective in limiting noise interference. To this end, we develop an adaptive connectivity estimation model that incorporates prior patterns, namely Sparse Adaptive Meta-Learning Connectivity Network (SAMCN). Specifically, our model extends ideas of the gradient-based meta-learning to capture inter-system shared prior information by generating fast adaptive initialization parameters for the connectivity matrix. Then, a sparse variational autoencoder is proposed to generate a weight matrix for sparse regularization penalty in reweighted LASSO, which helps extract intra-system intrinsic patterns (local manifold structure). Experimental results on both synthetic data and real-world datasets demonstrate that our method is capable of adequately capturing the aforementioned pattern priors. Further, experiments from corresponding classification tasks validate the strength of the prior pattern-aware features connectivity network in resulting in better classification performance.

While Point-of-Interest (POI) recommendation has been a popular topic of study for some time, little progress has been made for understanding why and how people make their decisions for the selection of POIs. To this end, in this paper, we propose a user decision profiling framework, named PROUD, which can identify the key factors in people's decisions on choosing POIs. Specifically, we treat each user decision as a set of factors and provide a method for learning factor embeddings. A unique perspective of our approach is to identify key factors, while preserving decision structures seamlessly, via a novel scalar projection maximization objective. Exactly solving the objective is non-trivial due to a sparsity constraint. To address this, our PROUD adopts a self projection attention and an L2 regularized sparse activation to directly estimate the likelihood of each factor to be a key factor. Finally, extensive experiments on real-world data validate the advantage of PROUD in preserving user decision structures. Also, our case study indicates that the identified key decision factors can help us to provide more interpretable recommendations and analyses.

The competitive relationship of Points of Interest (POIs) refers to the degree of competition between two POIs for business opportunities from third parties in an urban area. Existing studies for competitive analysis usually focus on mining competitive relationships of entities, such as companies or products, from textual data. However, there are few studies which have a focus on competitive analysis for POIs. Indeed, the growing availability of user behavior data about POIs, such as POI reviews and human mobility data, enables a new paradigm for understanding the competitive relationships among POIs. To this end, in this paper, we study how to predict the POI competitive relationship. Along this line, a very first challenge is how to integrate heterogeneous user behavior data with the spatial features of POIs. As a solution, we first build a heterogeneous POI information network (HPIN) from POI reviews and map search data. Then, we develop a graph neural network-based deep learning framework, named DeepR, for POI competitive relationship prediction based on HPIN. Specifically, DeepR contains two components: a spatial adaptive graph neural network (SA-GNN) and a POI pairwise knowledge extraction learning (PKE) model. The SA-GNN is a novel GNN architecture with incorporating POI's spatial information and location distribution by a specially designed spatial oriented aggregation layer and spatial-dependency attentive propagation mechanism. In addition, PKE is devised to distill the POI pairwise knowledge in HPIN being useful for relationship prediction into condensate vectors with relational graph convolution and cross attention. Finally, extensive experiments on two real-world datasets demonstrate the effectiveness of our method.

Multi-modal transportation recommendation aims to provide the most appropriate travel route with various transportation modes according to certain criteria. After analyzing large-scale navigation data, we find that route representations exhibit two patterns: spatio-temporal autocorrelations within transportation networks and the semantic coherence of route sequences. However, there are few studies that consider both patterns when developing multi-modal transportation systems. To this end, in this paper, we study multi-modal transportation recommendation with unified route representation learning by exploiting both spatio-temporal dependencies in transportation networks and the semantic coherence of historical routes. Specifically, we propose to unify both dynamic graph representation learning and hierarchical multi-task learning for multi-modal transportation recommendations. Along this line, we first transform the multi-modal transportation network into time-dependent multi-view transportation graphs and propose a spatiotemporal graph neural network module to capture the spatial and temporal autocorrelation. Then, we introduce a coherent-aware attentive route representation learning module to project arbitrary-length routes into fixed-length representation vectors, with explicit modeling of route coherence from historical routes. Moreover, we develop a hierarchical multi-task learning module to differentiate route representations for different transport modes, and this is guided by the final recommendation feedback as well as multiple auxiliary tasks equipped in different network layers. Extensive experimental results on two large-scale real-world datasets demonstrate the performance of the proposed system outperforms eight baselines.

The Takagi-Sugeno fuzzy model (T-S fuzzy model) has been successfully applied to a wide range of problems due to its accurate modeling ability. However, its rule redundancy and dimension disaster remain an open and unsolved issue. In this article, a novel fuzzy modeling method is proposed to reduce the fuzzy rule number without a loss in modeling accuracy. It includes two novel mechanisms: the rule fusion mechanism and the space projection mechanism. The rule fusion mechanism is developed to merge several rules into one according to similarity. In this way, the number of rules will greatly decrease. After the rules are merged, the relationship of data is strongly nonlinear, which renders the local linear model ineffective. In order to alleviate this difficulty, the space projection mechanism is then proposed to project the low-dimensional feature space to a high-dimension space. In this high-dimension space, the relation of data is linear and easily represented by a linear model. In this way, the traditional fuzzy inference is still applicative. With the help of these two mechanisms, a fuzzy model with few rules is constructed, which enables reconstruction of the nonlinear system. A solving method is then developed to determine the optimal parameters of the fuzzy model. Additional analysis and proof show that the proposed method exhibits the uniform approximation ability for strongly nonlinear systems. Case studies not only demonstrate the effectiveness of the proposed method, but also demonstrate its superior modeling performance in comparison to several conventional fuzzy modeling methods, even with the use of fewer rules.

A Point-of-Interest (POI) refers to a specific location that people may find useful or interesting. In modern cities, a large number of POIs emerge, grow, stabilize for a period, then finally disappear. The stages (e.g., emerge and grow) in this process are called lifetime statuses of a POI. While a large body of research has been devoted to identifying and recommending POIs, there are few studies on inferring the lifetime status of POIs. Indeed, the predictive analytics of POI lifetime status can be valuable for various tasks, such as urban planning, business site selection, and real estate appraisal. In this article, we propose a multitask learning approach, named inferring POI lifetime status, to inferring the POI lifetime status with multifaceted data sources. Specifically, we first define three types of POI lifetime status, i.e., booming, decaying, and stable. Then, we formulate a serial classification problem to predict the sequential/successive lifetime statuses of POIs over time. Leveraging geographical data and human mobility data, we examine and integrate three aspects of features related to the prosperity of POIs, i.e., region popularity, region demands, and peer competitiveness. Next, as the booming/decaying POIs are relatively rare in our data, we perform stable class decomposition to alleviate the imbalance between stable POIs and booming/decaying POIs. Finally, we develop a POI lifetime status classifier by exploiting the multitask learning framework as well as the multiclass kernel-based vector machines. We perform extensive experiments using large-scale and real-world datasets of New York City. The experimental results validate the effectiveness of our approach to automatically inferring POI lifetime status.

The least squares support vector machine (LS-SVM) is often employed to model data with a nonlinear distribution using a divide-and-conquer strategy. However, when nonlinear data are contaminated by either noise or outliers, LS-SVM is often an ineffective approach due to a lack of robustness. In this paper, a collaborative learning-based clustered LS-SVM method is proposed for modeling of nonlinear processes that are subject to noise or outliers. First, a large-scale dataset is divided into several subsets and the data distribution of each subset is estimated. A robust LS-SVM is then developed to represent each subset using this distributional information. A global model is further constructed through integration of all submodels, whose continuity and smoothness are ensured by the development of the collaborative learning technique. As a result, the proposed method considers both the nonlinear distribution of data and the robustness of each submodel, and ensures the continuity and smoothness of the global model. Thus, it can effectively model nonlinear data that is subject to either noise or outliers. As further validation of this approach, both artificial and real cases demonstrated its effectiveness.

Transportation recommendation is one important map service in navigation applications. Previous transportation recommendation solutions fail to deliver satisfactory user experience because their recommendations only consider routes in one transportation mode (uni-modal, e.g., taxi, bus, cycle) and largely overlook situational context. In this work, we propose Hydra, a recommendation system that offers multi-modal transportation planning and is adaptive to various situational context (e.g., nearby point-of-interest (POI) distribution and weather). We leverage the availability of existing routing engines and big urban data, and design a novel two-level framework that integrates uni-modal and multi-modal (e.g., taxi-bus, bus-cycle) routes as well as heterogeneous urban data for intelligent multi-modal transportation recommendation. In addition to urban context features constructed from multi-source urban data, we learn the latent representations of users, origin-destination (OD) pairs and transportation modes based on user implicit feedbacks, which captures the collaborative transportation mode preferences of users and OD pairs. A gradient boosting tree based model is then introduced to recommend the proper route among various uni-modal and multi-modal transportation routes. We also optimize the framework to support real-time, large-scale route query and recommendation. We deploy Hydra on Baidu Maps, one of the world's largest map services. Real-world urban-scale experiments demonstrate the effectiveness and efficiency of our proposed system. Since its deployment in August 2018, Hydra has answered over a hundred million route recommendation queries made by over ten million distinct users with 82.8% relative improvement of user click ratio.

Housing demand estimation is an important topic in the field of economic research. It is beneficial and helpful for various applications including real estate market regulation and urban planning, and therefore is crucial for both real estate investors and government administrators. Meanwhile, given the rapid development of the express industry, abundant useful information is embedded in express delivery records, which is helpful for researchers in profiling urban life patterns. The express delivery behaviors of the residents in a residential community can reflect the housing demand to some extent. Although housing demand has been analyzed in previous studies, its estimation has not been very good, and the subject remains under explored. To this end, in this article, we propose a systematic housing demand estimation method based on express delivery data. First, the express delivery records are aggregated on the community scale with the use of clustering methods, and the missing values in the records are completed. Then, various features are extracted from a less sparse dataset considering both the probability of residential mobility and the attractiveness of residential communities. In addition, given that the correlations between different districts can influence the performances of the inference model, the commonalities and differences of different districts are considered. After obtaining the features and correlations between different districts being obtained, the housing demand is estimated by using a multi-task learning method based on neural networks. The experimental results for real-world data show that the proposed model is effective at estimating the housing demand at the residential community level.

In recent years, bike-sharing systems have been widely deployed in many big cities, which provide an economical and healthy lifestyle. With the prevalence of bike-sharing systems, a lot of companies join the bike-sharing market, leading to increasingly fierce competition. To be competitive, bike-sharing companies and app developers need to make strategic decisions and predict the popularity of bike-sharing apps. However, existing works mostly focus on predicting the popularity of a single app, the popularity contest among different apps has not been explored yet. In this paper, we aim to forecast the popularity contest between Mobike and Ofo, two most popular bike-sharing apps in China. We develop CompetitiveBike, a system to predict the popularity contest among bike-sharing apps leveraging multi-source data. We extract two novel types of features: coarse-grained and fine-grained competitive features, and utilize Random Forest model to forecast the future competitiveness. In addition, we view mobile apps competition as a long-term event and generate the event storyline to enrich our competitive analysis. We collect data about two bike-sharing apps and two food ordering & delivery apps from 11 app stores and Sina Weibo, implement extensive experimental studies, and the results demonstrate the effectiveness and generality of our approach.

Estimation of housing requirement is beneficial for many applications such as guidance of house trading and real estate market regulation. Although there have been studies focusing on the demand analysis of urban resources, estimation of housing requirement is still under explored. To this end, in this paper we propose a systematic housing demand inference method, named Housing Demand Inference Model (HDIM), to estimate housing demand by exploiting the residential mobility of communities based on express delivery data. In this work, we first aggregate the express delivery records at community scale with clustering methods. Then, we propose a useful method to infer residential mobility by extracting express delivery related features and community related features. Since the features extracted are sparse for some residents, we utilize Regularized Singular Value Decomposition Model (RSVD) to construct missing values of features. After that, we infer residential mobility probability of each community by taking advantage of the less sparse features. We also consider community attractiveness as one of the factors influencing housing demand with the help of community profiles and geographical data. With the residential mobility probability and community attractiveness being obtained, we estimate housing demand with a regression model. Finally, experimental results on real-world data show that our model is effective to infer housing demand for communities in urban areas.

The extreme learning machine (ELM) has been extensively studied in the machine learning field and has been widely implemented due to its simplified algorithm and reduced computational costs. However, it is less effective for modeling data with non-Gaussian noise or data containing outliers. Here, a probabilistic regularized ELM is proposed to improve modeling performance with data containing non-Gaussian noise and/or outliers. While traditional ELM minimizes modeling error by using a worst-case scenario principle, the proposed method constructs a new objective function to minimize both mean and variance of this modeling error. Thus, the proposed method considers the modeling error distribution. A solution method is then developed for this new objective function and the proposed method is further proved to be more robust when compared with traditional ELM, even when subject to noise or outliers. Several experimental cases demonstrate that the proposed method has better modeling performance for problems with non-Gaussian noise or outliers.

The least-squares support vector machine (LS-SVM) is a popular data-driven modeling method and has been successfully applied to a wide range of applications. However, it has some disadvantages, including being ineffective at handling non-Gaussian noise as well as being sensitive to outliers. In this paper, a robust LS-SVM method is proposed and is shown to have more reliable performance when modeling a nonlinear system under conditions where Gaussian or non-Gaussian noise is present. The construction of a new objective function allows for a reduction of the mean of the modeling error as well as the minimization of its variance, and it does not constrain the mean of the modeling error to zero. This differs from the traditional LS-SVM, which uses a worst-case scenario approach in order to minimize the modeling error and constrains the mean of the modeling error to zero. In doing so, the proposed method takes the modeling error distribution information into consideration and is thus less conservative and more robust in regards to random noise. A solving method is then developed in order to determine the optimal parameters for the proposed robust LS-SVM. An additional analysis indicates that the proposed LS-SVM gives a smaller weight to a large-error training sample and a larger weight to a small-error training sample, and is thus more robust than the traditional LS-SVM. The effectiveness of the proposed robust LS-SVM is demonstrated using both artificial and real life cases.

Volatile Point-of-Interests (vPOIs) refer to those small businesses which appear and disappear quickly in cities. How to maintain and incubate small business in the urban area is a big concern for both business owners and government administrators. Therefore, the prediction task for the rise and fall of vPOIs is valuable for both shopkeepers and administrators by supporting a variety of applications in urban economics. In this paper, we propose a framework, named FRFP, to predict the prosperity of vPOIs over time. Specifically, due to the data sparsity and skewness of the individual vPOIs, we first aggregate vPOIs prosperities at focal areas w.r.t. each vPOI category. Then we develop the dynamic-continuous CRF (DC-CRF) model to integrate the association between input and output as well as the correlations between outputs from temporal, spatial and contextual perspectives. Finally, we conduct empirical experiments on real-world data from Google Maps and NYC OpenData. The evaluation results demonstrate that our proposed approach outperforms baseline algorithms with considerable margins. In addition, we explore the predictability of different explanatory variables and provide actionable insights for both shopkeepers and urban planners.

Point-of-Interest (POI) demand modeling in urban regions is critical for many applications such as business site selection and real estate investment. While some efforts have been made for the demand analysis of some specific POI categories, such as restaurants, it lacks systematic means to support POI demand modeling. To this end, in this paper, we develop a systematic POI demand modeling framework, named Region POI Demand Identification (RPDI), to model POI demands by exploiting the daily needs of people identified from their large-scale mobility data. Specifically, we first partition the urban space into spatially differentiated neighborhood regions formed by many small local communities. Then, the daily activity patterns of people traveling in the city will be extracted from human mobility data. Since the trip activities, even aggregated, are sparse and insufficient to directly identify the POI demands, especially for underdeveloped regions, we develop a latent factor model that integrates human mobility data, POI profiles, and demographic data to robustly model the POI demand of urban regions in a holistic way. In this model, POI preferences and supplies are used together with demographic features to estimate the POI demands simultaneously for all the urban regions interconnected in the city. Moreover, we also design efficient algorithms to optimize the latent model for large-scale data. Finally, experimental results on real-world data in New York City (NYC) show that our method is effective for identifying POI demands for different regions.

An effective model of the hydraulic actuator is crucial for high-accuracy driving control. However, modeling this driving process is difficult due to strong nonlinearities in the hydraulic system and load as well as unknown influence from sources of noise including sampling, modeling, measurement, and operation errors in the process. In this paper, a probabilistic weighted least square support vector machine (LS-SVM) is proposed to model this kind of processes under noise. The proposed method can increase robustness and accuracy even with outliers or non-Gaussian noise. First, a distribution construction method is developed to extract the probabilistic distribution of the distributed LS-SVM models caused by outliers and/or noise samples. Then, a new objective function is constructed using this distribution information to negate outlier or noise influence. Since this method considers the probabilistic information of outliers and/or noise samples, it has greatly improved the LS-SVM modeling capabilities in a noisy environment. Successful application of the proposed method to artificial cases and practical hydraulic actuators as well as comparison to several common modeling methods further highlight its superiority in modeling the nonlinear processes with noise.

Many industrial processes are complex nonlinear distributed parameter systems (DPSs) with time-varying spatiotemporal dynamics. However, time-varying spatiotemporal dynamics and the nonlinear relationships between spatial points are currently not given much consideration in the existing data-driven modeling methods. Thus, accurately modeling a nonlinear DPS with time-varying spatiotemporal dynamics using these current methods is challenging. Here, we propose a spatiotemporal extreme learning machine (ELM) to accurately model time-varying and nonlinear DPSs. First, we develop the nonlinear spatial activation function to describe the nonlinear relationships between spatial points. As a result, in contrast to the traditional ELM method which is only used to model the temporal dynamics, the spatiotemporal ELM inherently takes the spatial information into consideration. Next, an online time coefficient model is developed, which accounts for the time-varying temporal dynamics of the DPS. After the integration of the spatial activation function with the time coefficient model, this modeling method is able to adapt to real-time spatiotemporal variation. Unlike the existing data-driven DPS modeling approaches, the proposed method has the capability to accurately represent the nonlinear relationships between spatial points and has the adaptive ability for modeling time-varying dynamics. Finally, through application on practical curing experiments, the proposed method can improve the modeling precision for an unknown, time-varying, and nonlinear DPS due to smaller modeling error as compared to the several commonly used DPS modeling methods.

A Point of Interest (POI) refers to a specific location that people may find useful or interesting. While a large body of research has been focused on identifying and recommending POIs, there are few studies on characterizing the life cycle of POIs. Indeed, a comprehensive understanding of POI life cycle can be helpful for various tasks, such as urban planning, business site selection, and real estate evaluation. In this paper, we develop a framework, named POLIP, for characterizing the POI life cycle with multiple data sources. Specifically, to investigate the POI evolution process over time, we first formulate a serial classification problem to predict the life status of POIs. The prediction approach is designed to integrate two important perspectives: 1) the spatial-temporal dependencies associated with the prosperity of POIs, and 2) the human mobility dynamics hidden in the citywide taxicab data related to the POIs at multiple granularity levels. In addition, based on the predicted life statuses in successive time windows for a given POI, we design an algorithm to characterize its life cycle. Finally, we performed extensive experiments using large-scale and real-world datasets. The results demonstrate the feasibility in automatic characterizing POI life cycle and shed important light on future research directions.

The service usage analysis, aiming at identifying customers' messaging behaviors based on encrypted App traffic flows, has become a challenging and emergent task for service providers. Prior literature usually starts from segmenting a traffic sequence into single-usage subsequences, and then classify the subsequences into different usage types. However, they could suffer from inaccurate traffic segmentations and mixed-usage subsequences. To address this challenge, we exploit a multi-label multi-view learning strategy and develop an enhanced frame-work for in-App usage analytics. Specifically, we first devise an enhanced traffic segmentation method to reduce mixed-usage sub-sequences. Besides, we develop a multi-label multi-view logistic classification method, which comprises two alignments. The first alignment is to make use of the classification consistency between packet-length view and time-delay view of traffic subsequences and improve classification accuracy. The second alignment is to combine the classification of single-usage subsequence and the post-classification of mixed-usage subsequences into a unified multi-label logistic classification problem. Finally, we present extensive experiments with real-world datasets to demonstrate the effectiveness of our approach.

Recent years have witnessed the boom of venture capital industry. Venture capitalists can attain great financial rewards if their invested companies exit successfully, via being acquired or going IPO (Initial Public Offering). The literature has revealed that, from both financial and managerial perspectives, decision-making process and successful rates of venture capital (VC) investments can be greatly improved if the investors well know the team members of target startups. However, much less efforts have been made on understanding the impact of prominent social ties between the members of VC firms and start-up companies on investment decisions. To this end, we propose to study such social relationship and see how this information can contribute to foreseeing investment deals. We aim at providing analytical guidance for the venture capitalists in choosing right investment targets. Specifically, we develop a Social-Adjusted Probabilistic Matrix Factorization (PMF) model to exploit members social connections information from VC firms and startups for investment recommendations. Unlike previous studies, we make use of the directed relationship between any pair of connected members from the two institutions respectively and quantify the variety of social network groups. As a result, it brings in much more flexibility, and the modeling results inherently provide meaningful managerial implications for the operators of VC firms and startups. Finally, we evaluate our model on both synthetic and real-world data. The results demonstrate that our approach outperforms the baseline algorithms with a significant margin.

In online karaoke, the decision process in choosing a song is different from that in music radio, because users usually prefer songs that meet their vocal competence besides their tastes. Traditional music recommendation methods typically model users' personalized preference for songs in terms of content and style. However, this can be improved by considering the degree of matching the vocal competence (e.g. pitch, volume, and rhythm) of users to the vocal requirements of songs. To this end, in this paper, we develop a karaoke recommender system by incorporating vocal competence. Along this line, we propose a joint modeling method named CBNTF by exploiting the mutual enhancement between non-negative tensor factorization (NTF) and support vector machine (SVM). Specifically, we first extract vocal (i.e., pitch, volume, and rhythm) ratings of a user for a song from his/her singing records. Since these vocal ratings encode users' vocal competence from three aspects, we treat these vocal ratings as a tensor, exploit an NTF method, and learn the latent features of users' vocal metrics. These factorized features are simultaneously fed into an SVM classifier and then we use the trained classifier to predict the overall rating of a user with respect to a song. In addition, we propose an enhanced objective function to exploit the mutual enhancement between NTF and SVM, and devise an effective method to solve this objective as a coupled least-squares optimization problem via a maximum margin framework. With the estimated model, we compute the similarity between users and songs in terms of pitch, volume and rhythm and recommend songs to users. Finally, we conduct extensive experiments with real-world online karaoke data. The results demonstrate the effectiveness of our method.

The least-squares support vector machine (LS-SVM) has been successfully used to model nonlinear time dynamics; however, it does not have the capability to handle space information and is, therefore, unable to model the complex nonlinear distributed parameter systems (DPS). Here, we propose a spatiotemporal LS-SVM modeling method for complex nonlinear DPS. The space kernel function is developed to describe the nonlinear correlation between space locations. The time Lagrange multiplier represents the time dynamics. The integration of the space kernel function and the time Lagrange multiplier can reconstruct the nonlinear spatiotemporal dynamics of the DPS. The spatiotemporal LS-SVM method accounts for the time dynamics and the space distribution nature of the DPS, enabling it to adapt well to real-time spatiotemporal variation. The successful application of this spatiotemporal LS-SVM method to a practical curing thermal process and its comparison with several common DPS modeling methods demonstrate its superiority in the modeling of the unknown nonlinear distributed parameter process.

The rapid adoption of mobile messaging Apps has enabled us to collect massive amount of encrypted Internet traffic of mobile messaging. The classification of this traffic into different types of in-App service usages can help for intelligent network management, such as managing network bandwidth budget and providing quality of services. Traditional approaches for classification of Internet traffic rely on packet inspection, such as parsing HTTP headers. However, messaging Apps are increasingly using secure protocols, such as HTTPS and SSL, to transmit data. This imposes significant challenges on the performances of service usage classification by packet inspection. To this end, in this paper, we investigate how to exploit encrypted Internet traffic for classifying in-App usages. Specifically, we develop a system, named CUMMA, for classifying service usages of mobile messaging Apps by jointly modeling user behavioral patterns, network traffic characteristics, and temporal dependencies. Along this line, we first segment Internet traffic from traffic-flows into sessions with a number of dialogs in a hierarchical way. Also, we extract the discriminative features of traffic data from two perspectives: (i) packet length and (ii) time delay. Next, we learn a service usage predictor to classify these segmented dialogs into single-type usages or outliers. In addition, we design a clustering Hidden Markov Model (HMM) based method to detect mixed dialogs from outliers and decompose mixed dialogs into sub-dialogs of single-type usage. Indeed, CUMMA enables mobile analysts to identify service usages and analyze end-user in-App behaviors even for encrypted Internet traffic. Finally, the extensive experiments on real-world messaging data demonstrate the effectiveness and efficiency of the proposed method for service usage classification.

The least squares support vector machine (LS-SVM) has emerged as a popular data-driven modeling method and been extensively studied in the machine learning community. However, the LS-SVM is sensitive to noisy data and may not be effective when the level of noise is high. In this paper, a probabilistic LS-SVM is proposed to have a more reliable performance. First, a distributed LS-SVM is constructed with parameters estimated from data samples. Due to distributed nature of multiple LS-SVM, the stochastic property of parameters can be easily obtained and processed. Using the distribution characteristics of these parameters, the final outcome is derived through the probabilistic inference and thus be evaluated statistically. Its parallel structure is also suitable for parallel computing to reduce computing time. Both simulations and experiments demonstrate the effectiveness of the proposed probabilistic LS-SVM.

College students with financial difficulties refer to those whose families can hardly afford their high tuition in universities, and should be supported by modern funding system. Indeed, students' economic plight negatively impact their mental health, academic performance, as well as their personal and social life. While funding students in financial hardship is widely accepted, there is limited understanding and research on effectively identification of the qualifying students. Traditional approaches relying on advisers' personal assessments are inefficient, and such subjective judgements may not reflect the truth. To this end, in this paper, we explore the data mining techniques for identifying students who are qualified for financial support. Specifically, we investigate students' complex behaviors on campus from multiple perspectives, and develop a learning framework, named Dis-HARD, by jointly incorporating the heterogeneous features to predict the portfolio of stipends a given student should be awarded. Our framework formalizes the above problem as a multi-label learning problem. Along this line, we first extract discriminative features from three perspectives: (i) smartcard usage behavior, (ii) internet usage behavior and (iii) trajectory on campus. Then, we develop a linear loss function with regularization to solve this multi-label classification problem. In addition, to effectively exploit the students' similarity and label dependency, we incorporate the graph Laplacian and composite l2,1-norm into the regularization of our model, and develop are-weighted algorithm to achieve effective optimization. Finally, experiments on real-world data demonstrate that our method consistently provides better performance compared to the existing state-of-the-art methods.

An effective model of the forging process is crucial for the optimal operation and health management of a hydraulic press machine (HPM). Modeling this forging process is difficult, because multiple localized nonlinear solutions and modeling of unknown complex interactions between localized regions are required. In this paper, a novel least squares support vector machine (LS-SVM) method is developed for modeling the forging process. The proposed method integrates the advantages of local LS-SVM modeling and global regularization. Local LS-SVM modeling is performed to capture the local dynamics for each local working region. Global regularization is performed to minimize the global error and improve the global generalization of the local models. These features guarantee continuity and smoothness between the local LS-SVM models and avoid over-fitting of each local LS-SVM model. The algorithm developed here is simple and may easily be added into existing HPM systems. Experiment data from a practical HPM demonstrate the effectiveness of the proposed method.

An effective model of batch forging processes is crucial to ensure the quality conformance control of batch productions. However, obtaining this model has proven difficult due to a variety of the raw forgings produced by manufacturing error, material variation, geometric defects, etc. In this paper, a novel online probabilistic extreme learning machine (ELM) is proposed to model batch forging processes. A probabilistic ELM is first developed to extract the distribution information of the batch forging processes from the data. Due to the highly linear structure of the ELM, the stochastic property of the forging process is easily derived and processed. By using the characteristics of the online ELM, a strategy is then developed to update the distribution model as new forging process data are collected. Finally, case studies on complex batch forging processes demonstrate the effectiveness of the proposed online probabilistic ELM.

During the last decade, microblog has become an important social networking service with billions of users all over the world, acting as a novel and efficient platform for the creation and dissemination of real-time information. Modeling and revealing the information propagation patterns in microblogging services cannot only lead to more accurate understanding of user behaviors and provide insights into the underlying sociology, but also enable useful applications such as trending prediction, recommendation and filtering, spam detection and viral marketing. In this article, we aim to reveal the information propagation patterns in Sina Weibo, the biggest microblogging service in China. First, the cascade of each message is represented as a tree based on its retweeting process. Afterwards, we divide the information propagation pattern into two levels, that is, the macro level and the micro level. On one hand, the macro propagation patterns refer to general propagation modes that are extracted by grouping propagation trees based on hierarchical clustering. On the other hand, the micro propagation patterns are frequent information flow patterns that are discovered using tree-based mining techniques. Experimental results show that several interesting patterns are extracted, such as popular message propagation, artificial propagation, and typical information flows between different types of users.

Internet of Things (IoT) invasions a future in which digital and physical entities (e.g., mobile devices, wearable devices) can be linked, by means of appropriate information and communication technologies, to enable a whole new class of applications and services. In this paper, we study the dissemination of content over a mobile social network, which has become an attractive proxy for investigating human behaviors due to the rapid development of mobile phones. One of the most interesting and challenging problems about content dissemination is that how much attention of a specific post from a user can ultimately gain? Hence, in other words, can we forecast the crowds׳ concern in the mobile social networking environment, and how? We try to tackle this issue by exploring approaches to predict the amount of reposts any given post will obtain in Sina Weibo, a well-known mobile social networking service in China. We examine several novel implicit factors impacting the popularity of content, such as Modality, MaxMediaWeight and Activeness. Furthermore, we propose a RepostsTree based method to model the reposting process in a temporal dynamic manner. Experimental results over the collected data from Sina Weibo indicate that our method is effective on content diffusion prediction in mobile social networks.

In this paper, a new sub-domain intelligent modeling method based on neural networks is proposed for modeling the nonlinear multivariate process. The new modeling method decomposes the process into several levels sub-models and the low level models are the sub-model of the high level models. Since the modeling method is step by step to build the sub-models from low level models to high level models, it avoids the persistent excitation signal in multi-dimensions space, which is difficult to be produced due to the constraint of industry conditions. The accuracies and efficiencies of the modeling methodology are verified by simulation.