While user preferences are important to cross-domain recommendation (CDR), existing methods primarily discover preferences under specific, yet possibly redundant, item features. To this end, we first propose a novel Preference Prototype-Aware (PPA) learning method to quantitatively learn user preferences while minimizing disturbances from the source domain. It introduces a mix-encoder and a proto-decoder. On the one hand, the mix-encoder learns better general representations of interacted items and captures the intrinsic relationships between items across different domains. On the other hand, the proto-decoder implements a learnable prototype matching mechanism to quantitatively perceive user preferences, avoiding disturbances caused by item features from the source domain. Moreover, through experiments on PPA, we observe another two issues that affect existing CDR methods’ performance, i.e., the semantic deficiency caused by sparse item categories and the imbalance weights caused by different user-item distributions. Thus, we further propose a LoRA-based extractor and a domain cross-attention module to alleviate the two issues, respectively. The PPA incorporating with new extractor and attention module is called PPA++. Extensive experiments show that PPA++ outperforms the other state-of-the-art counterparts in four different CDR scenarios.

Recent advancements in Large Language Models (LLMs) have significantly extended context windows, igniting discussions about the necessity of Retrieval-Augmented Generation (RAG). U-NIAH, a unified Needle-in-a-Haystack (NIAH) framework, systematically evaluates LLMs and RAG methods in controlled long-context settings. It extends beyond traditional NIAH by incorporating more practical and complex scenarios like multi-needle, long-needle, and needle-in-needle configurations and leveraging the synthetic dataset to mitigate LLM biases. The experiments aim to address three research questions in long-context scenarios: (1) performance tradeoffs between LLMs and RAG, (2) error patterns in RAG, and (3) RAG’s limitations in complex settings. Results show that smaller LLMs benefit more from RAG. In all settings, RAG achieves a win rate of 82.58% over direct answers. Additionally, it is found that retrieval noise and chunk ordering degrade RAG performance, and we further summarized typical error patterns, including omissions due to noise, hallucinations under high noise critical conditions, and self-doubt behaviors, as well as how these phenomena vary with context length. Finally, in some challenging scenarios, experiments show that deep reasoning models are more easily affected by distractors. These findings highlight the complementary roles of RAG and LLMs and offer actionable insights for optimizing deployment strategies ( https://github.com/Tongji-KGLLM/U-NIAH ).

Intelligent question-answering (QA) systems powered by large language models (LLMs) have shown significant promise across various fields, but several challenges still hinder their application in mechanical manufacturing. This domain involves complex textual knowledge and numerous process design parameters, often presented in tabular form, which traditional LLMs struggle to extract effectively. We propose a novel intelligent QA system, MAR, tailored to address this in the mechanical manufacturing domain. MAR integrates open-source LLMs, Retrieval-Augmented Generation (RAG), and knowledge Re-ranking techniques. By combining RAG with Re-ranking, the system significantly enhances the accuracy and efficiency of knowledge retrieval, overcoming the limitations of traditional RAG methods. The system utilizes the LoRA+-fine-tuned Qwen2-7B model alongside a knowledge base containing industry standards and process design data. Experimental results show that the combination of RAG and Re-ranking outperforms traditional LLMs, as evidenced by improvements in BLEU-4 and ROUGE metrics. This research provides a practical solution for intelligent QA in mechanical manufacturing, effectively handling complex knowledge and precision-based tasks.

Retrieval Augmented Generation (RAG) has emerged as a promising solution to address hallucination issues in Large Language Models (LLMs). However, the integration of multiple retrieval sources, while potentially more informative, introduces new challenges that can paradoxically exacerbate hallucination problems. These challenges manifest primarily in two aspects: the sparse distribution of multi-source data that hinders the capture of logical relationships and the inherent inconsistencies among different sources that lead to information conflicts. To address these challenges, we propose MultiRAG, a novel framework designed to mitigate hallucination in multi-source retrieval-augmented generation through knowledge-guided approaches. Our framework introduces two key innovations: (1) a knowledge construction module that employs multi-source line graphs to efficiently aggregate logical relationships across different knowledge sources, effectively addressing the sparse data distribution issue; and (2) a sophisticated retrieval module that implements a multi-level confidence calculation mechanism, performing both graph-level and node-level assessments to identify and eliminate unreliable information nodes, thereby reducing hallucinations caused by inter-source inconsistencies. Extensive experiments on four multi-domain query datasets and two multi-hop QA datasets demonstrate that MultiRAG significantly enhances the reliability and efficiency of knowledge retrieval in complex multi-source scenarios. Our code is available in https://github.com/wuwenlong123/MultiRAG.

Retrieval-Augmented Generation (RAG) plays a vital role in enhancing large language models (LLMs) by enabling them to leverage external knowledge, thereby reducing hallucinations and improving the accuracy of responses. However, current RAG systems lack the capability to adjust retrieval strategies according to the complexity of queries. This inflexibility often leads to poor performance. To address this, we propose a novel Adaptive Retrieval-Augmented Generation framework. It employs an improved multi-armed bandit algorithm as a classifier for predicting query complexity. Treating each retrieval method as an ”arm”, the algorithm balances exploration and exploitation via Relative Performance. Experiments on multiple single-hop and multi-hop datasets demonstrate robust results: it outperforms traditional static RAG systems in both accuracy and efficiency, with significant gains in handling complex multi-hop queries while not adding unnecessary computational overhead for simple single-hop ones.

Heterogeneous hypergraph neural networks are powerful tools to capture complex correlations among various nodes in Heterogeneous Information Networks (HINs). Despite satisfied performances of them, they are still plagued by the following problems: 1) They cannot capture the correlations in structural and semantic view at once, leading to topological information loss. 2) Due to the number of nodes being greater than the number of node types, node-level self-attention they used causes massive parameters and leads to high time consumption. 3) Interactions in meta-paths may be redundant, resulting in the correlations bias. To address the three issues, we propose an efficientMulti-ViewHeterogeneousHypergraphConvolutionalNetwork (MVH$^{2}$GCN). It first constructs relational and semantic hypergraphs based on different types of edges and meta-paths respectively, to represent the complex correlations in structural view and semantic view. Meanwhile, the clean semantic hypergraphs are generated by structure learning network to avoid redundancy. Then, an efficient hypergraph convolutional network is designed to learn node embeddings. By doing so, correlations in the two views are captured. Finally, the learned node embeddings from two views are aggregated via a gated embedding fusion module for downstream tasks. Experiment results demonstrate that MVH$^{2}$GCN is effective and efficient.

A well-designed recommender system can accurately learn the embeddings of users and items, reflecting the unique preferences of users. Traditional recommendation techniques usually focus on modeling the singular type of behaviors between users and items. However, in many practical recommendation scenarios (e.g., social media, e-commerce), there exist multi-typed interactive behaviors in user–item relationships, such as click, tag-as-favorite, and purchase in online shopping platforms. Thus, how to make full use of multi-behavior information for recommendation is of great importance to the existing system, which presents challenges in two aspects that need to be explored: (1) Utilizing users’ personalized preferences to capture multi-behavioral dependencies; (2) Dealing with the insufficient recommendation caused by sparse supervision signal for target behavior. In this work, we propose the Knowledge Enhancement Multi-Behavior Contrastive Learning (KMCL) framework , including two Contrastive Learning tasks and three functional modules to tackle the above challenges, respectively. In particular, we design the multi-behavior learning module to extract users’ personalized behavior information for user-embedding enhancement and utilize knowledge graph in the knowledge enhancement module to derive more robust knowledge-aware representations for items. In addition, in the optimization stage, we also model the coarse-grained commonalities and the fine-grained differences between multi-behavior of users to further improve the recommendation effect and propose a joint training paradigm to enhance the learning effect of KMCLR in the joint learning module. Besides, we also considered how to make full use of temporal signals to enhance the effectiveness of multi-behavior recommendations in scenarios with time information and designed a novel encoder to address this issue. Extensive experiments and ablation tests on the three real-world datasets indicate that our KMCLR outperforms various state-of-the-art recommendation methods and verify the effectiveness of our method.

Identifying disinformation from online social media is crucial for maintaining a credible cyberspace. Although features from the content and propagation topology are widely exploited by existing studies to distinguish disinformation from normal ones, they are becoming less effective as content can be intentionally written to mislead readers and topological features are difficult to be extracted due to the high variance and diversity of reposting trees. Moreover, related works mainly focus on modeling the complete information propagation event, ignoring the staged evolution patterns along with propagation, which may also degrade the detection performance. In this paper, we conceive and implement a novel framework called DMPS for identifying disinformation, which Dynamically Models diverse topological structures of reposting trees as well as the textual content streams across different Propagation Stages. In particular, DMPS learns expressive representations of the structural features via meta-trees and extracts sequential features of the content for intra-stage modeling, then it captures temporal dependencies for inter-stage modeling. The whole framework is optimized in a binary classification manner. Experiments based on multilingual social media datasets validate the effectiveness and superiority of DMPS over state-of-the-art models. We believe that this study can provide insights for crisis management in response to disinformation in social network campaigns.

Cross-domain recommendation (CDR) aims to suggest items from new domains that align with potential user preferences, based on their historical interactions. Existing methods primarily focus on acquiring item representations by discovering user preferences under specific, yet possibly redundant, item features. However, user preferences may be more strongly associated with interacted items at higher semantic levels, rather than specific item features. Consequently, this item feature-focused recommendation approach can easily become suboptimal or even obsolete when conducting CDR with disturbances of these redundant features. In this paper, we propose a novel Preference Prototype-Aware (PPA) learning method to quantitatively learn user preferences while minimizing disturbances from the source domain. The PPA framework consists of two complementary components: a mix-encoder and a preference prototype-aware decoder, forming an end-to-end unified framework suitable for various real-world scenarios. The mix-encoder employs a mix-network to learn better general representations of interacted items and capture the intrinsic relationships between items across different domains. The preference prototype-aware decoder implements a learnable prototype matching mechanism to quantitatively perceive user preferences, which can accurately capture user preferences at a higher semantic level. This decoder can also avoid disturbances caused by item features from the source domain. The experimental results on public benchmark datasets in different scenarios demonstrate the superiority of the proposed PPA learning method compared to state-of-the-art counterparts. PPA excels not only in providing accurate recommendations but also in offering reliable preference prototypes. Our code is available at https://github.com/zyx-nuaa/PPA-for-CDR.

During infectious disease outbreaks, tracking contacted objects is important for suppressing the spread of the virus and using trajectories of moving objects to discover contacted objects is one of effective approaches. Existing algorithms focus on individual contact event discovery but lack the ability to obtain the k-degree contact events. In this paper, we propose efficient k-degree contact pattern mining algorithms that are capable of mining k-degree contact events. The definition of k-degree contact event is first formulated. Based on the definition, a sliding window-based baseline k-degree contact pattern mining algorithm (KCPMA) is presented. To improve the mining efficiency, the sample-point checking strategy and R-tree index are adopted and the optimized mining algorithm (KCPMA+) is proposed. Comprehensive experiments on real datasets demonstrate that the proposed algorithms are effective and efficient in mining k-degree contact events.

The less developed sensor technologies of traditional civil elevators, particularly in older districts, have long impeded the construction of smart cities. By using surveillance cameras, we can intelligently identify the abnormal events in elevator, but there is currently a lack of relevant datasets. For this purpose, we curate a visual elevator anomalous events dataset that serves as a benchmark for evaluating the performance of state-of-the-art detection models like YOLOv8. Then we improved YOLOv8 via adding coordinate attention and optimizing loss functions and activation functions, resulting in a notable enhancement in its performance for elevator abnormal detection. Furthermore, based on the improved model we implement a system called ELEvent in a real residential community and proved effective in practice.

Accurate classification of encrypted traffic is vital for effective network management and Quality of Service (QoS). Protocol identification and application recognition are central to this process. Existing solutions generally use separate models for protocol identification and application recognition. However, running these models in parallel in online environments significantly increases system complexity, resource consumption, and maintenance costs. Additionally, these models often suffer from poor traffic representation by discarding crucial byte information and retaining irrelevant biases. This paper introduces an efficient multi-task learning framework, ELEMTC, designed to simultaneously perform protocol identification and application recognition, while offering a tailored traffic representation scheme for network management. To improve efficiency, we propose a novel sample pre-training task, Detection Token Replacement, specifically tailored for the networking domain. Experimental results on the ISCX VPN-non VPN dataset show that ELEMTC achieves Fl scores of 98.37% and 99.46% for application recognition and protocol identification, respectively. These results demonstrate that ELEMTC significantly outperforms current state-of-the-art methods. Furthermore, ELEMTC demonstrates outstanding efficiency by improving inference speed 20 times while maintaining relatively low memory usage.

Existing knowledge graph query approaches, whether traditional textual query languages or visual query languages, have steep learning curves that are unfriendly for non-expert users. This demonstration presents a Visual Query approach based on Full-Text search for knowledge graphs, called VQFT, which simplifies the process of querying knowledge graphs for users. Inspired by full-text search techniques, VQFT aims to combine the user-friendliness of visual query with the intuitiveness of full-text search , enabling users to query knowledge graphs as straightforward as using a search engine. Faceted full-text indexes, visual query constructor , and an interactive user interface are designed to achieve this goal. User tests and surveys have demonstrated that VQFT is more user-friendly and easier to learn than existing methods, which simplifies the construction of knowledge graph queries for non-expert users.

We study the problem of processing continuous$k$nearest neighbor (C$k$NN) queries over moving objects on road networks, which is an essential operation in a variety of applications. We are particularly concerned with scenarios where the object densities in different parts of the road network evolve over time as the objects move. Existing methods on C$k$NN query processing are ill-suited for such scenarios as they utilize index structures with fixed granularities and are thus unable to keep up with the evolving object densities. In this paper, we directly address this problem and propose an object density aware index structure called ODIN that is an elastic tree built on a hierarchical partitioning of the road network. It is equipped with the unique capability of dynamically folding/unfolding its nodes, thereby adapting to varying object densities. We further present the ODIN-KNN-Init and ODIN-KNN-Inc algorithms for the initial identification of the$k$NNs and the incremental update of query result as objects move. Thorough experiments on both real and synthetic datasets confirm the superiority of our proposal over several baseline methods.

Knowledge graphs (KGs) are commonly used as side information to enhance collaborative signals and improve recommendation quality. In the context of knowledge-aware recommendation (KGR), graph neural networks (GNNs) have emerged as promising solutions for modeling factual and semantic information in KGs. However, the long-tail distribution of entities leads to sparsity in supervision signals, which weakens the quality of item representation when utilizing KG enhancement. Additionally, the binary relation representation of KGs simplifies hyper-relational facts, making it challenging to model complex real-world information. Furthermore, the over-smoothing phenomenon results in indistinguishable representations and information loss.

Using trajectories of moving objects and performing contact event query during disease transmission is an effective method of prevention and control. Existing contact query processing algorithms only consider single-source (one-to-one) contact event and thus can not discover multi-source (n-to-one) contact events. In this paper, we propose efficient multi-source contact event query processing methods that are capable of querying multi-source contact events. The definition of multi-source contact events is first formulated. Then, a baseline multi-source contact event query processing algorithm is presented, which adopts the idea of sliding window-based sequential scanning. To improve the query efficiency, the 2-dimensional bitmap filter and the anchor time point scanning are designed and used in the optimized query processing algorithm. Comprehensive experiments on real-world data demonstrate that the proposed algorithms can find more potential contact events and have good performance in the manner of query time cost.

A well-designed recommender system can accurately capture the attributes of users and items, reflecting the unique preferences of individuals. Traditional recommendation techniques usually focus on modeling the singular type of behaviors between users and items. However, in many practical recommendation scenarios (e.g., social media, e-commerce), there exist multi-typed interactive behaviors in user-item relationships, such as click, tag-as-favorite, and purchase in online shopping platforms. Thus, how to make full use of multi-behavior information for recommendation is of great importance to the existing system, which presents challenges in two aspects that need to be explored: (1) Utilizing users' personalized preferences to capture multi-behavioral dependencies; (2) Dealing with the insufficient recommendation caused by sparse supervision signal for target behavior. In this work, we propose a Knowledge Enhancement Multi-Behavior Contrastive Learning Recommendation (KMCLR) framework, including two Contrastive Learning tasks and three functional modules to tackle the above challenges, respectively. In particular, we design the multi-behavior learning module to extract users' personalized behavior information for user-embedding enhancement, and utilize knowledge graph in the knowledge enhancement module to derive more robust knowledge-aware representations for items. In addition, in the optimization stage, we model the coarse-grained commonalities and the fine-grained differences between multi-behavior of users to further improve the recommendation effect. Extensive experiments and ablation tests on the three real-world datasets indicate our KMCLR outperforms various state-of-the-art recommendation methods and verify the effectiveness of our method.

Abstract Patient similarity search is an essential task in healthcare. Recent studies adopted electronic health records (EHRs) to learn patient representations for measuring the clinical similarities. These methods outperformed traditional methods, by capturing more information from various sources consisting of multi-modal EHRs, external knowledge and correlations among medical concepts. They often concerned certain type of data without taking full advantage of various information. We propose a graph representation learning framework, denoted by One-Size-Fits-Three ( OSFT ), that takes into account fusion-attention, neighbor-attention and global-attention from three types of information. Extensive experiments are conducted on two real datasets of MIMIC-III and MIMIC-IV, and the results verified the effectiveness and generality of our framework. When compared with baselines on patient similarity search, our framework achieved good effectiveness and comparative efficiency. The results provide new insights about whether the use of various information can better measure the patient similarity. The source codes are available at https://github.com/emmali808/ADDS/tree/master/EHRDeepHelper .

Abstract Advanced knowledge engineering (KE), represented by knowledge graph (KG), drives the development of various fields and engineering technologies and provides various knowledge fusion and knowledge empowerment interfaces. At the same time, advanced system engineering (SE) takes model-based system engineering (MBSE) as the core to realize formal modeling and process analysis of the whole system. The two complement each other and are the key technologies for the transition from 2.0 to 3.0 in the era of artificial intelligence and the transition from perceptual intelligence to cognitive intelligence. This survey summarizes an advanced information fusion system, from model-driven to knowledge-enabled. Firstly, the concept, representative methods, key technologies and application fields of model-driven system engineering are introduced. Then, it introduces the concept of knowledge-driven knowledge engineering, summarizes the architecture and construction methods of advanced knowledge engineering and summarizes the application fields. Finally, the combination of advanced information fusion systems, development opportunities and challenges are discussed.

As an essential part of mobile networks, vehicular ad hoc networks (VANETs) are beneficial to the improvement of traffic efficiency and safety through real-time information sharing between vehicles. Digital Twins (DT) have been utilized to facilitate the design, testing, and deployment of VANETs. However, constructing Digital Twins still faces interference from malicious vehicles. Despite most vehicles following communication rules honestly, the reliability and authenticity of traffic messages cannot be guaranteed due to the network’s openness and vulnerability. Meanwhile, vehicles may suffer tracking attacks during the interaction without an effective privacy-preserving method, leading to the leakage of sensitive data. To address these issues, a decentralized trust management scheme embedded with blockchain that considers identity authentication is proposed to detect malicious DT-vehicles. In our method, each vehicle in the Digital Twin of VANETs (DT-VANETs) is equipped with a certificate recorded on the blockchain as a legal identity, which is also served as a pseudonym for security during message transmission. The trustworthiness of the vehicle is evaluated based on direct trust and recommendation trust. Direct interaction between vehicles consists of message authenticity verification and active detection, which are the basis of direct trust calculation. For other vehicles, these direct trust opinions are treated as second-hand information to obtain recommendation trust. Unreliable recommendations are filtered by our proposed RTF algorithm, further resisting cooperation attacks. Vehicles judged to be malicious will have their certificates revoked and removed from DT-VANETs, providing a guarantee for the establishment of trust in DT-VANETs. Experimental results show that the proposed scheme can effectively resist malicious attacks in DT-VANETs.

Recent advancement in propulsion technologies to reduce the need for travel or increase the share of sustainable unmanned devices has accelerated the shift toward sustainable transport. To achieve the optimization of route planning in the air-ground integrated network (AGIN), we design an optimization strategy of accompanying graph navigation for unmanned devices, which aims to reduce the power consumption and$CO_{2}$gas emissions. The optimization of accompanying graph navigation is composed of three strategies, namely, the navigation based on the complete maps, the navigation based on the partitioned maps, and the navigation without maps. We propose a Two-tiered Grid (TG) index and Distributed AGIN Navigation (DAN) to navigate on partitioned maps. The top layer of the TG-index is composed of the border vertices of the global road network, which reflects the overall traffic conditions of the global road network and provides coarse-grained navigation routes. The bottom layer is a grid index composed of subgraphs, which reflects traffic conditions in local areas and provides fine-grained navigation routes. The navigation optimization is implemented in several segments, which can be run by multi-processors and realize rapid response to a large number of concurrent queries.

Route planning over dynamic road networks is an increasingly fundamental problem of modern transportation systems for human society, especially in the field of Intelligent Supply Chain (ISC). Due to the high degree of urbanization and the high number of vehicles, longer response time caused by massive concurrent queries, as well as more attacks caused by malicious vehicles, results in low efficiency of the transportation system and huge waste of computation resources. Thus, it is necessary to provide an efficient and safe transportation service for intelligent transportation planning. To achieve it, we utilize and improve the trust model to prevent the waste of computation resources. Meanwhile, we introduce a Trusted Parallel Optimization on Route Planning (T-PORP) based on Dual-level Grid (DLG) index to continuously handle the process of route planning in parallel. Considering the evolving traffic condition, we employ an LSTM (Long Short-Term Memory) neural network to periodically predict the weights of roads. Experimental results indicate that T-PORP is effective to sorts of trust model attacks and reduces the response time by an average of about 46.7% and saves the processing time by an average of about 27.6% compared with CANDS (Continuous Optimal Navigation via Distributed Stream Processing) algorithm.

Automated vehicle(AV) based on reinforcement learning is an important part of the intelligent transportation system. However, currently, the performance of AV heavily that relies on the quality of maps and mapless navigation is one potential method for navigation in a strange and dynamic changing environment. Although many efforts are made on mapless navigation, they either need prior knowledge, rely on an exceptional constructed environment or simple feature fusion mechanism in the networks. In this paper, we proposed a deep reinforcement learning method, namely TC-DDPG, which is consisted of DDPG, multi-challenge deep learning networks and time-critical reward function. By comparing to existing approaches, TC-DDPG takes the cost of time into consideration and achieves better performance and converges more easily. A new open source simulator is proposed and extensive experiments are conducted to demonstrate the performance of the TC-DDPG, which outperforms comparing methods and achieves 62.9% less in time cost, 12.0% less in distance cost and about 90% fewer in numbers of model parameters.

In Internet of Vehicles (IoV), the vehiclead hocnetwork (VANET) provides the location-based service (LBS) when vehicles communicate with the dynamic environment. As an integration of satellite systems and terrestrial communications, the space–air–ground integrated network (SAGIN) provides a reliable and efficient way for LBS. But the privacy protection in SAGIN cannot meet LBS security requirements well, so we present a blockchain-based LBS security preserving trust model.$K$-anonymous location privacy protection algorithm is used to hide users’ real position so that users can avoid personal privacy disclosure when requesting LBSs. We propose a trust management algorithm which can detect the malicious behaviors when constructing anonymous regions and clear the malicious users out of the system. Besides, we use blockchain to implement the transparency and conditional anonymity of the system. Missive experiments indicate that our scheme is feasible and outperforms part of state-of-the-art privacy protection approaches.

With the popularity of mobile devices equipped with positioning devices, it is convenient to obtain enormous amounts of trajectory data. The development promotes the study of extracting moving patterns from trajectory data of moving objects. One such pattern is the convoy, which refers to a group of objects moving together for a period of time. The existing convoy mining algorithms have a large time cost because they adopt a density-based clustering algorithm over global objects. In this paper, we propose an efficient convoy mining algorithm (ECMA) that adopts the divide-and-conquer methodology. A block-based partition model (BP-Model) is designed to divide objects into multiple maximized connected nonempty block areas (MOBAs). The convoy mining problem is then solved by processing each MOBA sequentially, which significantly reduces the time cost of convoy mining. In the experiments, we evaluate the performance of our algorithm on real-world datasets. The results show that the ECMA is more efficient than existing convoy mining algorithms.

Sequential recommendation systems seek to learn users' preferences to predict their next actions based on the items engaged recently. Static behavior of users requires a long time to form, but short-term interactions with items usually meet some actual needs in reality and are more variable. RNN-based models are always constrained by the strong order assumption and are hard to model the complex and changeable data flexibly. Most of the CNN-based models are limited to the fixed convolutional kernel. All these methods are suboptimal when modeling the dynamics of item-to-item transitions. It is difficult to describe the items with complex relations and extract the fine-grained user preferences from the interaction sequence. To address these issues, we propose a knowledge-aware sequential recommender with the attention-enhanced dynamic convolutional network (KAeDCN). Our model combines the dynamic convolutional network with attention mechanisms to capture changing dependencies in the sequence. Meanwhile, we enhance the representations of items with Knowledge Graph (KG) information through an information fusion module to capture the fine-grained user preferences. The experiments on four public datasets demonstrate that KAeDCN outperforms most of the state-of-the-art sequential recommenders. Furthermore, experimental results also prove that KAeDCN can enhance the representations of items effectively and improve the extractability of sequential dependencies.

We are pleased to present a special issue of Data Science and Engineering (DSE), which contains a collection of six extended papers from the APWeb-WAIM 2020 conference.We also include a regular submission paper in this issueAPWeb-WAIM conferences focus on research, development, and applications in relation to Web information management, including a wide range of topics, such as text analysis, graph data processing, social networks, recommender systems, information retrieval, data streams, knowledge graph, data mining and application, query processing, machine learning, database and Web applications, big data, and blockchain.

The problem of route planning on road network is essential to many Location-Based Services (LBSs). Road networks are dynamic in the sense that the weights of the edges in the corresponding graph constantly change over time, representing evolving traffic conditions. Thus, a practical route planning strategy is required to supply the continuous route optimization considering the historic, current, and future traffic condition. However, few existing works comprehensively take into account these various traffic conditions during the route planning. Moreover, the LBSs usually suffer from extensive concurrent route planning requests in rush hours, which imposes a pressing need to handle numerous queries in parallel for reducing the response time of each query. However, this issue is also not involved by most existing solutions. We therefore investigate a parallel traffic condition driven route planning model on a cluster of processors. To embed the future traffic condition into the route planning, we employ a GCN model to periodically predict the travel costs of roads within a specified time period, which facilitates the robustness of the route planning model against the varying traffic condition. To reduce the response time, a Dual-Level Path (DLP) index is proposed to support a parallel route planning algorithm with the filter-and-refine principle. The bottom level of DLP partitions the entire graph into different subgraphs, and the top level is a skeleton graph that consists of all border vertices in all subgraphs. The filter step identifies a global directional path for a given query based on the skeleton graph. In the refine step, the overall route planning for this query is decomposed into multiple sub-optimizations in the subgraphs passed through by the directional path. Since the subgraphs are independently maintained by different processors, the sub-optimizations of extensive queries can be operated in parallel. Finally, extensive evaluations are conducted to confirm the effectiveness and superiority of the proposal.

Effective querying of data in the road networks is an important problem in the Internet of vehicles. Aggregate nearest neighbor queries can return the objects that minimizes an aggregate distance function on road networks considering a set of query points in the Internet of vehicles. And${k}$aggregate nearest neighbor query (${k}$- ANN) is a complicate version for the basic one. The existing${k}$- ANN queries lack effective model to deal with the uncertain data and the existing query methods cannot be applied to solve the problem of (${k}$- ANN) query on uncertain data directly. Therefore, in this paper, a probabilistic threshold${k}$- ANN query method based on uncertain Voronoi diagram is proposed. The method includes three phases: processing phase, pruning phase and refinement phase. The processing phase is to compute the minimum covered circle of the query dataset which is prepared for the pruning phase. In pruning phase, the different pruning algorithms are proposed for the corresponding three aggregate function of aggregate nearest neighbor query. The data points that cannot be the result are pruned and the candidate set is obtained. In refinement phase, the sets composed of${k}$data points in candidate set whose probabilities are not less than the user-specified threshold are stored into the result set and returned to the user. Experiments are performed to evaluate the effectiveness and superiority of these algorithms on probabilistic thresholdk-ANNquery.

Vehicular ad hoc network(VANET) is a special mobile ad hoc network (MANET) which plays an important role in the intelligent traffic system(ITS). Based on the high mobility of VANETs, the security problems have not been reasonably solved when we enjoy the convenience brought by the Location Based Service(LBS). We present a blockchain-based trust management model for location privacy preserving. The scheme allows vehicles to use certificate to request LBS without revealing their privacy information. We construct anonymous cloaking region to ensure the privacy security of vehicles. We propose a trust management algorithm to constrain and standardize the behavior of vehicles, and use blockchain to implement the data security of vehicles. In the experiments, we conduct the tests with various data sets. Security analysis and experiments show that the system is resilient to sorts of trust model attacks, which can better preserve the privacy security of vehicles. Simulation results reveal that the proposed system is effective and feasible in collect.

Resume block classification is the most significant step in resume information extraction. However, the existing algorithms applied to resume block classification are all the general text classification algorithms, which failed to consider the contextual order of each block within a resume. In order to improve the performance of resume block classification, we propose in this paper a block-level bidirectional recurrent neural network model that makes full use of the contextual order relationship among different resume blocks. The experimental results show that the average F1-score value of our model on three 1,400 real resume datasets is 6% to 9% higher than the existing methods.