Xueqing Li

INTI International University | inti

Aiming for creating a convenient and intelligent living environment for city dwellers, recommender systems have been used to provide consumers with personalized suggestions when shopping or using public services. Among these systems, the metric learning (MtL)-based method often employs the Euclidean distance between user and item representations to...

Cyber-Physical systems, as the cornerstone of smart city, has been attracting great interest from academia and industry. It aims to monitor/ control physical components via communication and computation, while ensuring effectiveness, intelligence, and security. The related research has pointed that the state perception on physical device is the pre...

Graph convolution networks (GCNs) play an increasingly vital role in recommender systems, due to their remarkable relation modeling and representation capabilities. Concretely, they can capture high-order semantic correlations within sparse bipartite interaction graphs, thereby enhancing user–item collaborative encodings. Despite the exciting prosp...

Along with the sustainable and rapid accumulation of user-generated contents in social networking websites, how to push a certain content to the corresponding interested users, named recommendation for short, has successfully received wide attention. Considering the continuous updated contents and the constant changing of users’ interests, recommen...

Along with the coming of industry 4.0 era, industrial internet of things (IIoT) plays a vital role in advanced manufacturing. It can not only connect all equipment and applications in manufacturing processes closely, but also provide oceans of sensor data for real-time work-in-process monitoring. Considering the corresponding abnormalities existing...

With the proliferation of IoMT (Internet of Medical Things), billions of connected medical devices are constantly producing oceans of time series sensor data, dubbed as time series for short. Considering these time series reflect various functional states of the human body, how to effectively detect the corresponding abnormalities is of great signi...

Recommender systems, which merely leverage user-item interactions for user preference prediction (such as the collaborative filtering-based ones), often face dramatic performance degradation when the interactions of users or items are insufficient. In recent years, various types of side information have been explored to alleviate this problem. Amon...

Recent years have witnessed the exponential growth of time series data as the popularity of sensing devices and development of IoT techniques; time series classification has been considered as one of the most challenging studies in time series data mining, attracting great interest over the last two decades. According to the empirical evidences, te...

A multiview synthetic aperture radar (SAR) target recognition with discrimination and correlation analysis is proposed in this study. The multiple views are first prescreened by a support vector machine (SVM) to select out those highly discriminative ones. These views are then clustered into several view sets, in which images share high correlation...

Streaming time series retrieval (TSR) has been widely concerned in academia and industry. Considering the large volume, high dimensionality and continuous accumulation features of time series, there is limited capability to perform in-depth similarity searching directly on the raw time series data. Therefore, time series representation, which can p...

This paper proposes a novel head pose estimation scheme that is based on image and wavelets input and conducts a coarse to fine regression. As wavelets provide low-level shape abstractions, we add them as extra channels to the input to help the neural network to make better estimation and converge. We design a coarse-to-fine regression framework th...

This letter develops a synthetic aperture radar (SAR) target classification method based on bidimensional variational mode decomposition (BVMD) and multitask compressive sensing (MTCS). BVMD is employed to decompose SAR images to exploit the time-frequency properties of the described targets. The MTCS is used to jointly classify the original SAR im...

The evolution of IoT has increased the popularity of all types of sensing devices in a variety of industrial fields and has resulted in enormous growth in the volume of sensor data. Considering the high volume and dimensionality of sensor data, the ability to perform in-depth data analysis and data mining tasks directly on the raw time series senso...

In the process of building an ontology-based knowledge base, developers need to transform the knowledge within the domain into a system conceptual framework that can be processed. This process is usually divided into two parts: knowledge acquisition and knowledge representation. If the way of acquiring knowledge is arbitrary, it is easy to form a c...

Content-based human motion capture (MoCap) data retrieval facilitates reusing motion data that have already been captured and stored in a database. For a MoCap data retrieval system to get practically deployed, both high precision and natural interface are demanded. Targeting both, we propose a video-based human MoCap data retrieval solution in thi...

With the burgeoning of IoE (Internet of Everything), massive numbers of IoT devices in extensive fields are continuously producing huge number of streaming time series. The high dimensionality and dynamic uncertainty of this kind of data lead to the main challenge on traditional time series data mining research. Accordingly, time series representat...

Time series similarity search has been widely used in many applications, such as financial data analysis, meteorological data forecasting, and multimedia data retrieval. The original task of this research was to find time series in a database similar to the query sequence, where both the results and the query sequence are static. However, along wit...

With the rapid development of information technology, we have already access to the era of big data. Time series is a sequence of data points associated with numerical values and successive timestamps. Time series not only has the traditional big data features, but also can be continuously generated in a high speed. Therefore, it is very time- and...

Nowadays, with the proliferation of IoT (Internet of Things), we have gradually entered into a new IoE (Internet of Everything) era, in which billions of connected devices in widespread fields are constantly producing oceans of streaming time series. In order to conduct in-depth data mining researches (similarity searching, classification, clusteri...

Database is an indispensable part of software development. In order to reduce unnecessary and redundant processes of accessing in database, the concept of Object-Relational Mapping (ORM) has been proposed and its corresponding applications have been widely accepted by developers. However, for a certain software system, accessing database systems is...

In recent years, domain adaptation methods have aroused much interest in the machine learning community which transfer labeled information from the source domain to the target domain. However, most of the domain adaptation methods require that the source domain and target domain share the same features which may limit the applications of these appr...

Over the last decade, huge number of time series stream data are continuously being produced in diverse fields, including finance, signal processing, industry, astronomy and so on. Since time series data has high-dimensional, real-valued, continuous and other related properties, it is of great importance to do dimensionality reduction as a prelimin...

Visual analytics play an important role in understanding complex datasets. The bibliographic database is often visualized as a collaboration network to illustrate the connections between researchers. Static networks, however, barely reveal any information when the dataset includes temporal variables. In this article, we propose an embedded network...

With the burgeoning of IoE (Internet of Everything), massive numbers of IoT devices in entensive fields are continuously producing huge number of time series, named as streaming time series (STS). The high dimensionality and dynamic uncertainty of STS ead to the main challenge on traditional time series data mining research. Accordingly, time serie...

Water inrush is a geological hazard often encountered in tunnel construction. In order to overcome problems encountered when using the existing water-inrush simulation model test, such as single function, low repetition utilization rate, and poor visibility, we developed a multi-type water-inrush model test system. Our test system can be a precurso...

Association rules are one of the important methods of Data Mining, but the traditional association rule algorithm requires multiple scans of the database, with high I/O overhead and failure to handle node failure and load balancing. MapReduce is a popular distributed parallel computing model with good scalability and automatic load balancing and ha...

Interactive visual analysis plays an important role to understand complex dataset. Literature data are most often visualized as collaboration networks to show the connection between researchers. However, the static networks barely transfer much information when the dataset including temporal variable. In this paper, we propose an embedded network v...

Along with the coming of IoE (Internet of Everything) era, massive numbers of pervasive connected devices in various fields are continuously producing oceans of time series stream data, which is characterized by its large amount, high dimensionality and continuity nature. In order to carry out different kinds of data mining tasks (similarity search...

With the rapid development of Internet of things (IoT), we have gradually entered into the IoE (Internet of everything) era. In face of the low quality of real-time gathering sensor data in IoT, this paper proposes a novel real-time anomaly detection algorithm based on edge computing for streaming sensor data. This algorithm firstly expresses the c...

In the recent years, manifold learning methods have been widely used in data classification to tackle the curse of dimensionality problem, since they can discover the potential intrinsic low-dimensional structures of the high-dimensional data. Given partially labeled data, the semi-supervised manifold learning algorithms are proposed to predict the...

Along with the coming of IoT (Internet of things) era, massive numbers of instruments and applications in various fields are continuously producing oceans of time series stream data, which could be characterized by its large amount, high dimensionality and continuity nature. In order to carry out different kinds of data mining tasks (similarity sea...

Along with the arrival of Industry 4.0 era, massive numbers of detecting instruments in various fields are continuously producing a plenty number of time series stream data. In order to efficiently and effectively analyze and mine the high-dimensional streaming time series, the segmentation which provides more accurate representation to the raw tim...

In recent years, manifold alignment methods have aroused a great of interest in the machine learning community which construct a common latent space shared by multiple input data sets. In a semi-supervised problem, it is assumed that some predetermined correspondences are available to us. The effectiveness of the semi-supervised manifold alignment...

Motif discovery is a method for finding some previously unknown but frequently appearing patterns in time series. However, the high dimensionality and dynamic uncertainty of time series data lead to the main challenge for searching accuracy and effectiveness. In our paper, we propose a novel k-motifs discovery approach based on the Piecewise Linear...

In the process of high education informationization, unstructured data sharing plays an important part in the business integration. Due to the diversity and large volume of unstructured data, it is very difficult to share unstructured data. In this paper, we investigated on the problems of data sharing among different departments in high education...

Course Similarity Calculation aims at quantitatively computing the cross degree of the knowledge points two courses contain. However, the polysemy and synonym of various knowledge points lead to the main challenge for calculation effectiveness. Existing course similarity calculation methods are mainly based on the traditional text mining approaches...

The double-random phase encryption (DRPE) algorithm is a robust technique for image encryption, due to its high speed and encoding a primary image to stationary white noise. Recently it was reported that DRPE in the Fresnel domain can achieve a better avalanche effect than that in Fourier domain, which means DRPE in the Fresnel domain is much safer...

The performance of component-based software (CBS) has been a challenge of component technology as it can improve the flexibility of CBS. Optimizing the performance of CBS has been focused by academia and industry until now and is also the main content of this paper. First, one framework for supporting component-based development (CBD) was given to...

Text visualization method depends on the contents of documents to analyze patterns and abstract characters. Words set or semantic relationships often get involved. However, visualizing the large scholar text as an understandable view for users is a challenging. We propose an interactive model to describe the scholar information by statistical work...

To improve the efficiencyof software testing, a model-driven method is proposed to automatically generatetest cases from UML design model. In it, PITCs (platform-independent testcases) are generated first from a UML design model. And then, according to thepredefined rules, a process is implemented to transform PITCs into thecorresponding PSTCs (pla...

DXF File is a graph exchanging file for CAD data exchange between other softwares provided by Autodesk Company. The house drawing of Shandong University is designed by AutoCAD software, and the graph information of house is recorded by the DXF file. Based on the DXF file, this paper will conduct an analysis on DXF file and extract the information f...

Text visualization method depends on the contents of documents to analyze patterns and abstract characters. However, visualizing the scholar text as an understandable view for users is a challenging. We propose an interactive model to collect, analyze, and visualize coauthoring data of publication information. We divide the author into students and...

Point-based 3D model simplification is closely related to hierarchical clustering techniques that may be classified into agglomerative, divisive and hybrid ones. In this paper, we propose a novel divisive-clustering based algorithm, improve a hybrid-clustering based algorithm and investigate an agglomerative-clustering based algorithm for point-bas...

This paper analyses problem-based learning (PBL) process and involving various data types. We bring forward a "centralism transmission-distribution computation" hybrid computation model in terms of the data time-property and characteristics. The model adopts multiple layers soft architecture for ensuring the system scalability and suitability, obta...

This paper designs and implements a development framework that fits the development of educational management information system (EMIS), and provides an interface-generated user interface management system (UIMS) components and flexible permissions management modules. Considering the complex technological process of business in EMIS, we implements...

The feature matching is the first step of several computer vision duties. In this paper we provide a new feature detect and matching approach based on statistics of the gradients of the feature region. It is extension of the sift algorithm. The algorithm represented in this paper can be used to perform reliable matching to image sequence, which hav...