Time series classification has ubiquitous applications in the real world. Owing to its importance, many time series classification techniques have been proposed over years. Among them, neural network based methods have attracted significant research attention due to their ability to automatically extract latent and discriminative features from data. In this paper, we explorerelationship features, which provide valuable global information for time series analytics, and propose a general neural network architecture, namelyRel-CNN, to learn both global and local subsequence features for time series classification. Moreover, we provide two detailed model designs,Relationship Feature based Convolution FilteringandLatent Relationship Feature based Convolution Filtering, and address technical issues due to excessive parameters to learn in these models. We evaluate our models and baselines on time series classification, with extensive experiments on the widely-used 85 uni-variate “bake-off” datasets and 8 multi-variate UEA datasets. Experimental results show that our Rel-CNN models are superior to the representative time series classifiers, in terms of average accuracy, average Macro-f1 and ranking metrics. In addition, an ensemble version of Rel-CNN also outperforms the state-of-the-art ensemble classifiers in terms of average rank, average accuracy and average Macro-f1 on the bake-off datasets.

Learning to route has received significant research momentum as anew approach for the route planning problem in intelligent transportation systems. By exploring global knowledge of geographical areas and topological structures of road networks to facilitate route planning, in this work, we propose a novel Generative Adversarial Network (GAN) framework, namely Progressive Route Planning GAN (ProgRPGAN), for route planning in road networks. The novelty of ProgRPGAN lies in the following aspects: 1) we propose to plan a route with levels of increasing map resolution, starting on a low-resolution grid map, gradually refining it on higher-resolution grid maps, and eventually on the road network in order to progressively generate various realistic paths; 2) we propose to transfer parameters of the previous-level generator and discriminator to the subsequent generator and discriminator for parameter initialization in order to improve the efficiency and stability in model learning; and 3) we propose to pre-train embeddings of grid cells in grid maps and intersections in the road network by capturing the network topology and external factors to facilitate effective model learn-ing. Empirical result shows that ProgRPGAN soundly outperforms the state-of-the-art learning to route methods, especially for long routes, by 9.46% to 13.02% in F1-measure on multiple large-scale real-world datasets. ProgRPGAN, moreover, effectively generates various realistic routes for the same query.

Citations of scientific papers and patents reveal the knowledge flow and usually serve as the metric for evaluating their novelty and impacts in the field. Citation Forecasting thus has various applications in the real world. Existing works on citation forecasting typically exploit the sequential properties of citation events, without exploring the citation network. In this paper, we propose to explore both the citation network and the related citation event sequences which provide valuable information for future citation forecasting. We propose a novel \em Citation Network and Event Sequence (CINES) Model to encode signals in the citation network and related citation event sequences into various types of embeddings for decoding to the arrivals of future citations. Moreover, we propose atemporal network attention and three alternative designs of \em bidirectional feature propagation to aggregate the retrospective and prospective aspects of publications in the citation network, coupled with the citation event sequence embeddings learned by a \em two-level attention mechanism for the citation forecasting. We evaluate our models and baselines on both a U.S. patent dataset and a DBLP dataset. Experimental results show that our models outperform the state-of-the-art methods, i.e., RMTPP, CYAN-RNN, Intensity-RNN, and PC-RNN, reducing the forecasting error by 37.76% - 75.32%.

Informative representation of road networks is essential to a wide variety of applications on intelligent transportation systems. In this article, we design a new learning framework, called Representation Learning for Road Networks (RLRN), which explores various intrinsic properties of road networks to learn embeddings of intersections and road segments in road networks. To implement the RLRN framework, we propose a new neural network model, namely Road Network to Vector (RN2Vec), to learn embeddings of intersections and road segments jointly by exploring geo-locality and homogeneity of them, topological structure of the road networks, and moving behaviors of road users. In addition to model design, issues involving data preparation for model training are examined. We evaluate the learned embeddings via extensive experiments on several real-world datasets using different downstream test cases, including node/edge classification and travel time estimation. Experimental results show that the proposed RN2Vec robustly outperforms existing methods, including (i) Feature-based methods : raw features and principal components analysis (PCA); (ii) Network embedding methods : DeepWalk, LINE, and Node2vec; and (iii) Features + Network structure-based methods : network embeddings and PCA, graph convolutional networks, and graph attention networks. RN2Vec significantly outperforms all of them in terms of F1-score in classifying traffic signals (11.96% to 16.86%) and crossings (11.36% to 16.67%) on intersections and in classifying avenue (10.56% to 15.43%) and street (11.54% to 16.07%) on road segments, as well as in terms of Mean Absolute Error in travel time estimation (17.01% to 23.58%).

In this article, we propose a novel representation learning framework, namely TRajectory EMBedding via Road networks (Trembr) , to learn trajectory embeddings (low-dimensional feature vectors) for use in a variety of trajectory applications. The novelty of Trembr lies in (1) the design of a recurrent neural network--(RNN) based encoder--decoder model, namely Traj2Vec , that encodes spatial and temporal properties inherent in trajectories into trajectory embeddings by exploiting the underlying road networks to constrain the learning process in accordance with the matched road segments obtained using road network matching techniques (e.g., Barefoot [24, 27]), and (2) the design of a neural network--based model, namely Road2Vec , to learn road segment embeddings in road networks that captures various relationships amongst road segments in preparation for trajectory representation learning. In addition to model design, several unique technical issues raising in Trembr, including data preparation in Road2Vec, the road segment relevance-aware loss, and the network topology constraint in Traj2Vec, are examined. To validate our ideas, we learn trajectory embeddings using multiple large-scale real-world trajectory datasets and use them in three tasks, including trajectory similarity measure, travel time prediction, and destination prediction. Empirical results show that Trembr soundly outperforms the state-of-the-art trajectory representation learning models, trajectory2vec and t2vec , by at least one order of magnitude in terms of mean rank in trajectory similarity measure, 23.3% to 41.7% in terms of mean absolute error (MAE) in travel time prediction, and 39.6% to 52.4% in terms of MAE in destination prediction.

Estimating the travel time for a given path is a fundamental problem in many urban transportation systems. However, prior works fail to well capture moving behaviors embedded in paths and thus do not estimate the travel time accurately. To fill in this gap, in this work, we propose a novel neural network framework, namely Deep Image-based Spatio-Temporal network (DeepIST), for travel time estimation of a given path. The novelty of DeepIST lies in the following aspects:1) we propose to plot a path as a sequence of -generalized images"which include sub-paths along with additional information, such as traffic conditions, road network and traffic signals, in order to harness the power of convolutional neural network model (CNN)on image processing; 2) we design a novel two-dimensional CNN, namely PathCNN, to extract spatial patterns for lines in images by regularization and adopting multiple pooling methods; and 3) we apply a one-dimensional CNN to capture temporal patterns among the spatial patterns along the paths for the estimation. Empirical results show that DeepIST soundly outperforms the state-of-the-art travel time estimation models by 24.37% to 25.64% of mean absolute error (MAE) in multiple large-scale real-world datasets

Road network is a basic component of intelligent transportation systems (ITS) in smart city. Informative representation of road networks is important as it is essential to a wide variety of ITS applications. In this paper, we propose a neural network representation learning model, namely Intersection of Road Network to Vector (IRN2Vec), to learn embeddings of road intersections that encode rich information in a road network by exploring geo-locality and intrinsic properties of intersections and moving behaviors of road users. In addition to model design, several issues unique to IRN2Vec, including data preparation for model training and various relationships among intersections, are examined. We evaluate the learned embeddings via extensive experiments on three real-world datasets using three downstream test cases, including prediction of traffic signals and crossings on intersections and travel time estimation. Experimental results show that the proposed IRN2Vec outperforms three existing methods, DeepWalk, LINE and Node2vec, in terms of F1-score in predicting traffic signals (22.21% to 23.84%) and crossings (8.65% to 11.65%), and mean absolute error (MAE) in travel time estimation (9.87% to 19.28%).

In this paper, we propose a novel representation learning framework, namely HIN2Vec, for heterogeneous information networks (HINs). The core of the proposed framework is a neural network model, also called HIN2Vec, designed to capture the rich semantics embedded in HINs by exploiting different types of relationships among nodes. Given a set of relationships specified in forms of meta-paths in an HIN, HIN2Vec carries out multiple prediction training tasks jointly based on a target set of relationships to learn latent vectors of nodes and meta-paths in the HIN. In addition to model design, several issues unique to HIN2Vec, including regularization of meta-path vectors, node type selection in negative sampling, and cycles in random walks, are examined. To validate our ideas, we learn latent vectors of nodes using four large-scale real HIN datasets, including Blogcatalog, Yelp, DBLP and U.S. Patents, and use them as features for multi-label node classification and link prediction applications on those networks. Empirical results show that HIN2Vec soundly outperforms the state-of-the-art representation learning models for network data, including DeepWalk, LINE, node2vec, PTE, HINE and ESim, by 6.6% to 23.8% of $micro$-$f_1$ in multi-label node classification and 5% to 70.8% of $MAP$ in link prediction.

The extant work on network analyses has thus far paid little attention to the heterogeneity in time lags and speed of information propagation along edges. In this paper, we study this novel problem, modeling the time dimension and lags on network edges, in the context of paper and patent citation networks where the variation in the speed of knowledge flows between connected nodes is apparent. We propose to model time lags in knowledge diffusions in citation networks in one of the two ways: deterministic lags and probabilistic lags. Then, we discuss two approaches of computationally working with time lags in edges of citation networks. Experimentally, we study two different applications to demonstrate the importance of the time dimension and lags in citations: (1) HITS algorithm and (2) patent citation recommendation. We conduct experiments on millions of U. S. patent data and Web of Science (WOS) paper data. Our experiments show that incorporating time dimension and lags in edges significantly improve network modeling and analyses.

There is a consensus that U. S. patent examiners, who are responsible for identifying prior art relevant to adjudicationof patentability of patent applications, often lack thetime, resources and/or experience necessary to conduct adequateprior art search. This study aims to build an automatic andeffective system of patent citation recommendation for patentexaminers. In addition to focusing on content and bibliographicinformation, our proposed system considers another importantpiece of information that is known by patent examiners, namely, applicant citations. We integrate applicant citations and bibliographicinformation of patents into a heterogeneous citationbibliographicnetwork. Based on this network, we explore metapathsbased relationships between a query patent application anda candidate prior patent and classify them into two categories:(1) Bibliographic meta-paths, (2) Applicant Bibliographic metapaths. We propose a framework based on a two-phase rankingapproach: the first phase involves selection of a candidate subsetfrom the whole U. S. patent data, and the second phase usessupervised learning models to rank prior patents in the candidatesubset. The results show that both bibliographic informationand applicant citation information are very useful for examinercitation recommendation, and that our approach significantlyoutperforms a search engine.

Wireless sensor networks have been proposed for facilitating various monitoring applications (e.g., environmental monitoring and military surveillance) over a wide geographical region. In these applications, spatial queries that collect data from wireless sensor networks play an important role. One such query is the K-Nearest Neighbor (KNN) query that facilitates collection of sensor data samples based on a given query location and the number of samples specified (i.e., K). Recently, itinerary-based KNN query processing techniques, which propagate queries and collect data along a predetermined itinerary, have been developed. Prior studies demonstrate that itinerary-based KNN query processing algorithms are able to achieve better energy efficiency than other existing algorithms developed upon tree-based network infrastructures. However, how to derive itineraries for KNN query based on different performance requirements remains a challenging problem. In this paper, we propose a Parallel Concentric-circle Itinerary-based KNN (PCIKNN) query processing technique that derives different itineraries by optimizing either query latency or energy consumption. The performance of PCIKNN is analyzed mathematically and evaluated through extensive experiments. Experimental results show that PCIKNN outperforms the state-of-the-art techniques.

This paper proposes the CFE framework---Composition, Feedback, and Evolution---and presents an interactive music composition system. The system composes short, manageable pieces of music by interacting with users. The most important features of the system include creating customized music according to the user preference and providing the facilities specifically designed for producing large amounts of music. We present the structure as well as the implementation of the system and the auxiliary functionalities that enhance the system. We also introduce the auto-feedback test with which we verify and evaluate the interactive music composition system.