In the field of multivariate time series analysis, data incompleteness, such as missing data due to measurement errors or equipment failures, is a common issue that severely hinders in-depth analysis and decision-making for downstream tasks. Existing time series imputation models have made progress in fitting the overall data distribution but lack the ability to analyze data features from multiple perspectives. This limitation hinders a deeper understanding of the data features, thereby affecting the reliability and generalization performance of the imputation results. For the limitation of existing models, this paper proposes a novel time series imputation model based on multiple guidance distillation, MGDTSI. This model uses self-distillation, by using teacher models of different majors, to strengthen the ability of student model. To distinguish the guiding capabilities of different teachers, the weight fusion module is used to assign weights to different teacher models to jointly guide the student model. The experimental results conducted on multiple public time series datasets show that MGDTSI significantly outperforms the existing baseline methods in the task of missing value imputation.

Recently around half of the world’s current population resides in urban areas and benefit from rich services in the smart city. The majority of smart city services are recommendation-related services, and with the development of Internet, most recommendation services in smart economy are online recommendations. Online travel platforms (OTPs) (like Booking, Airbnb, Ctrip, and Fliggy) provide people sufficient resources and convenient approaches to plan and enjoy their trips in smart city. Hotel recommendation is essential for the success of OTPs. However, it is more challenging compared to item recommendation in typical E-commerce scenarios (e.g., Taobao, Jd, and YouTube). The in-nature characteristics of low-frequency and high unit-price lead to more severe sparse and long-tail data distributions. Moreover, for enhancing user experience and business returns, the recommender system seeks to improve both click-through rate (CTR) and conversion rate (CVR) where the seesaw phenomenon may occur. In order to address the aforementioned shortages in hotel recommendation, a multitask learning (MTL) method with a novel flexible multilevel extraction network [denoted as flexible MTL (FMTL)] is proposed. Particularly, FMTL takes MTL into consideration in a unified representation learning framework and is divided into feature encoding and task prediction. In the feature encoding phase, we introduce a novel multirepresentation extractor with temperature-adjusted gating mechanism (T-MRE) for each task, producing more flexible representations for sparse and long-tail data. Moreover, we fuse different representations for each task with three strategies during the prediction phase and empirically demonstrate that the simple concatenation strategy is superior than other relatively complex gating approaches. Offline and live experiments with regard to both overall metrics and user group analysis based on the scarcity of user behaviors illustrate that without significantly increasing model parameters, our FMTL model outperforms substantially over several state-of-the-art models.

Extending the length of time series forecasting has a long-term impact on smart grid energy consumption planning, residential electricity monitoring, extreme weather warning, and other real applications. This article studies the reliable long-term load trend forecasting approaches in smart grid environment. In recent years, the improved neural networks models based on self-attention mechanism show good performances in many sequence tasks, but most studies focus on reducing the complexity of networks layer, and can not restrain the increase of calculation error in longer distance forecasting scenarios. Also, most models lack the ability to mine potential high-dimensional features of time series. Based on these problems, we design a reliable hierarchical self-attention model named as long-term stability network (LTSNet), which adopts a tree-shaped decomposition neural network architecture based on hierarchical residual self-attention blocks, to top-down incrementally mine high-dimensional features of temporal components. At the same time, the attention matrix is used for feature interaction at each layer, to reduce the distribution gap between time series fragments in different domains. Compared with existing study models, LTSNet maintains stable forecasting performance and speed in long-term forecasting services, achieved the most reliable multivariate and univariate forecasting results in multiple domain scenarios. Compared with the latest models, the forecasting accuracy of the proposed model is improved by 22.8% and 13.8%, respectively, covering three applications: energy consumption, residential electricity consumption, and weather forecasting. At the same time, our experiments verify that the hierarchical decomposition networks can be used as a backbone architecture to effectively extended to longer dimensional load trend forecasting scenarios.

Name ambiguity issue that results from the similarity of many common Chinese names. With the development of artificial intelligence, the disambiguation model based on machine learning has achieved better disambiguation effects and has been widely used in various universities. However, continually improving the disambiguation effect remains a major challenge. Smart campuses based on the Internet of Things are developing rapidly, and a large number of discretely distributed web tables that omit data values exist. However, the usable attributes of the disambiguation model are limited. To overcome these challenges, this study proposes a name disambiguation model of web tables from data integration (NDWT) in smart campuses. The model first recognises the label mapping in a webpage table using four types of label matchers and then designs the instance comparator based on the obtained label mapping. The web tables are integrated according to the instance mapping relationship, and two datasets, one before (BWT) and the other after (A WT) integration, are obtained. Relevant features are subsequently extracted from these two datasets and trained. Finally, the NDWT model is used for disambiguation experiments. Comparative experiments, condu-cted using seven different types of ML models, show that the NDWT model improves significantly after the integration of web tables; in particular, the pairwise F1 of the K-means model increases by 43.23%. The pairwise F1 of the remaining models increases by approximately 10%. The experimental evaluation proves the feasibility of the NDWT model proposed in this study. Confirming that it can achieve a higher distribution quality compared to conventional name disambiguation methods.

Nowadays, artificial neural networks are widely used for users’ online travel planning. Personalized travel planning has many real applications and is affected by various factors, such as transportation type, intention destination estimation, budget limit and crowdness prediction. Among those factors, users’ intention destination prediction is an essential task in online travel platforms. The reason is that, the user may be interested in the travel plan only when the plan matches his real intention destination. Therefore, in this paper, we focus on predicting users’ intention destinations in online travel platforms. In detail, we act as online travel platforms (such as Fliggy and Airbnb) to recommend travel plans for users, and the plan consists of various vacation items including hotel package, scenic packages and so on. Predicting the actual intention destination in travel planning is challenging. Firstly, users’ intention destination is highly related to their travel status (e.g., planning for a trip or finishing a trip). Secondly, users’ actions (e.g. clicking, searching) over different product types (e.g. train tickets, visa application) have different indications in destination prediction. Thirdly, users may mostly visit the travel platforms just before public holidays, and thus user behaviors in online travel platforms are more sparse, low-frequency and long-period. Therefore, we propose a Deep Multi-Sequences fused neural Networks (DMSN) to predict intention destinations from fused multi-behavior sequences. Real datasets are used to evaluate the performance of our proposed DMSN models. Experimental results indicate that the proposed DMSN models can achieve high intention destination prediction accuracy.

As the emerging paradigm that is believed to be conducive to the development of intelligent transportation systems (ITS), Internet of Vehicles (IoV) is constructed with a number of connected heterogeneous vehicle devices which provide a variety of services. As the number of vehicle devices in IoV is growing fast, selecting the appropriate service from candidate services which are functionally equivalent is becoming an imperative task. Predicting the non-functional attribute of service invocation, namely quality of service (QoS), to ensure the optimal service selection is the mainstream direction. Considering that most of the conventional prediction methods neglect the fact that QoS values change dynamically with some objective factors, this paper proposes a recurrent neural network based collaborative filtering method called RNCF for QoS prediction. Specifically, a multi-layer GRU structure is incorporated in the framework of neural collaborative filtering to model the dynamic state of physical environments or network conditions and share the invocation records across different time slices. We conduct extensive experiments on the WSDream dataset to demonstrate the effectiveness of the proposed QoS prediction model RNCF.

With the enormous growth of the content and users of social network, user portrait based on social network have been widely used in industrial applications such as artificial intelligence, recommendation systems, etc. The issue has been extensively studied, and most of them have focused on user attribute mining and behavior prediction. However, there is little research on the intrinsic relationship between big data-based interests and skills and occupational adaptability. To clarify this issue, in this article, we first collect a large amount of user data from LinkedIn. Then, we filter high-frequency interests and skills, and explore relevant characteristics of interests and skills through relevant analytical methods, found that there are many association rules. Next, the users are grouped according to the characteristics of occupational adaptability, and the relationship between the association rules of interests and skills and user adaptability is studied. Finally, designed an occupational adaptive classifier based on association rules. This article reveals the connections and dependencies between human interests and professional skills, as well as the impact of these association rules on user career adaptability, also discusses the prospects of these results in industrial applications. We hope that our research results will provide a solid theoretical foundation for other areas of research and industrial applications, such as career adaptability judgment, interest training, career development, career recommendation, etc.

Container enables a new way to run applications by containerizing the application, which provides kinds of services to make them portable, extensible, and easy to be transferred between private data centers and public clouds.Comparing with virtual machines, containers have several advantages in terms of simplicity, low-overhead and lightweight.However, as the OS kernel and resources are shared by all the hosted containers, performance isolation becomes a challenging issue for guaranteeing their SLA.This paper discusses I/O performance isolation issue in container-based clusters.First, we analyze the characteristics of I/O performance isolation from the perspective of the SLA.Then we conduct the observation experiments using multiple containers to obtain the variation trend of the I/O performance parameters and observe the impact of the I/O overload container on the I/O performance isolation of the system.Finally, we propose two algorithms, SLAE and UTE, to improve the I/O performance isolation in container-based systems.These algorithms contribute to decrease the interference caused by the overloaded containers.Experimental results show the feasibility and effectiveness of our proposed algorithms.

Summary Parallel semi‐implicit method for pressure‐linked equations(SIMPLE) algorithm is used to solve the 3‐D incompressible pipe flow problem. In this paper, we proposed a novel parallel SIMPLE algorithm that uses the alternate tiling technique. Firstly, a parallel SIMPLE algorithm based on domain decomposition method was established, and the implementation of domain partition and data exchange was presented. Then, we presented serial finite difference stencil algorithm based on alternate tiling. Furthermore, an iteration space parallel two‐way finite difference stencil algorithm based on alternate tiling was proposed, introducing the sequence of iterative space tiles as the sequence of execution and using time skewing technique to partition the iteration space, thus to improve the data locality of algorithm. The cache misses and the cost of communication and synchronization are reduced by reordering the tiles of iteration space. Finally, the effectiveness of the two parallel SIMPLE algorithms were compared. The results showed that the parallel SIMPLE algorithm that uses the two‐way finite difference stencil algorithm based on alternate tiling has good data locality, performance, and scalability in the Deepcomp7000 cluster computing environment. Copyright © 2013 John Wiley & Sons, Ltd.