Xiangjian He - Profile on Academia.edu (original) (raw)

Papers by Xiangjian He

CCF Transactions on Pervasive Computing and Interaction, 2020

With the emerging concepts of smart cities and intelligent transportation systems, accurate traff... more With the emerging concepts of smart cities and intelligent transportation systems, accurate traffic sensing and prediction have become critically important to support urban management and traffic control. In recent years, the rapid uptake of the Internet of Vehicles and the rising pervasiveness of mobile services have produced unprecedented amounts of data to serve traffic sensing and prediction applications. However, it is significantly challenging to fulfill the computation demands by the big traffic data with ever-increasing complexity and diversity. Deep learning, with its powerful capabilities in representation learning and multi-level abstractions, has recently become the most effective approach in many intelligent sensing systems. In this paper, we present an up-to-date literature review on the most advanced research works in deep learning for intelligent traffic sensing and prediction.

Web servers and web-based applications are commonly used as attack targets. The main issues are h... more Web servers and web-based applications are commonly used as attack targets. The main issues are how to prevent unauthorised access and to protect web servers from the attack. Intrusion Detection Systems (IDSs) are widely used security tools to detect cyber-attacks and malicious activities in computer systems and networks. In this paper, we focus on the detection of various web-based attacks using Geometrical Structure Anomaly Detection (GSAD) model and we also propose a novel algorithm for the selection of most discriminating features to improve the computational complexity of payload-based GSAD model. Linear Discriminant method (LDA) is used for the feature reduction and classification of the incoming network traffic. GSAD model is based on a pattern recognition technique used in image processing. It analyses the correlations between various payload features and uses Mahalanobis Distance Map (MDM) to calculate the difference between normal and abnormal network traffic. We focus on ...

Quantum Information Processing, 2018

Quantum Fourier transform (QFT) plays a key role in many quantum algorithms, but the existing cir... more Quantum Fourier transform (QFT) plays a key role in many quantum algorithms, but the existing circuits of QFT are incomplete and lacking the proof of correctness. Furthermore, it is difficult to apply QFT to the concrete field of information processing. Thus, we firstly investigate quantum vision representation (QVR) and develop a model of QVR (MQVR). Then, we design four complete circuits of QFT and inverse QFT (IQFT) and describe the functions of their components. Meanwhile, we prove the correctness of the four complete circuits using formula derivation. Next, 2D QFT and 3D QFT based on QVR are proposed for the first time. Experimental results with simulation show the proposed QFTs are valid and useful in processing quantum images and videos. In conclusion, this paper develops a complete framework of QFT based on QVR and provides a feasible scheme for QFT to be applied in quantum vision information processing.

Information Sciences, 2019

A mobile social network (MSN) consists of certain amount of mobile users with social characterist... more A mobile social network (MSN) consists of certain amount of mobile users with social characteristics, and it provides data delivery concerning social relationships between mobile users. In MSN, ordinary people contact each other more frequently if they have more social features in common. In this paper, we apply a new topology structure-priority relation graph (PRG) to evaluate the data delivery routing in MSN on the system-level. By using the natural order of nodes' representation, the diameter, the regular degree and the multi-path technology, we determine the priority relation graphbased social feature routing (PRG-SFR) algorithm to find disjointed multi-paths in MSN. Here, the multi-path technology can be exploited for ensuring that, between each pair of sender and receiver, the important information can be delivered through a highly reliable path. Then we calculate the tolerant ability of 'faults' and estimate the availability of MSN on the theoretical level. Finally, we analyze the efficiency of PRG-SFR algorithm from the numerical standpoint in terms of fault tolerance, forwarding number, transmission time and delivery rate. Moreover, we make comparisons between PRG-SFR algorithm and certain state-of-the-art technologies.

Computer Vision – ECCV 2012. Workshops and Demonstrations, 2012

In this work, we present a C++ implementation of object categorization with the bag-of-word (BoW)... more In this work, we present a C++ implementation of object categorization with the bag-of-word (BoW) framework. Unlike typical BoW models which consider the whole area of an image as the region of interest (ROI) for visual codebook generation, our implementation only considers the regions of target objects as ROIs and the unrelated backgrounds will be excluded for generating codebook. This is achieved by a supervised mean shift algorithm. Our work is on the benchmark SIVAL dataset and utilizes a Maximum Margin Supervised Topic Model for classification. The final performance of our work is quite encouraging.

Journal of Electronic Imaging, 2015

It is a challenging task to develop an effective and robust object tracking method due to factors... more It is a challenging task to develop an effective and robust object tracking method due to factors such as severe occlusion, background clutters, abrupt motion, illumination variation and so on. In this paper, a novel tracking algorithm based on weighted subspace reconstruction error is proposed. The discriminative weights are defined through minimizing reconstruction error with positive dictionary while maximizing reconstruction error with negative dictionary. Then, confidence map for candidates is computed through subspace reconstruction error. Finally, the location of the target object is estimated by maximizing the decision map which is combined discriminative weights and subspace reconstruction error. Furthermore, the new evaluation method based on forward-backward tracking criterion to verify the robustness of the current tracking performance in updating stage, which can reduce the accumulated error effectively. Experimental results on some challenging video sequences show that the proposed algorithm performs favorably against eleven state-of-the-art methods in terms of accuracy and robustness.

2008 IEEE International Conference on Data Mining Workshops, 2008

A new feature description is used for human behaviour representation and recognition. The feature... more A new feature description is used for human behaviour representation and recognition. The feature is based on Radon Transform of extracted silhouettes. Key postures are selected based on the transform feature. Key postures are summed up to represent each sequence. Linear Discriminant Analysis (LDA) is applied to the sum of key postures to obtain low dimensional feature vectors. Different classification methods are used to classify each sequence. Experiments are carried on a public human behaviour database and the result is exciting.

The popularity of using internet contains some risks of network attacks. It has attracted the att... more The popularity of using internet contains some risks of network attacks. It has attracted the attention of many researchers to overcome this problem. One of the effective ways that plays an important role to achieve higher security and protect networks against attacks is the use of intrusion detection systems. Intrusion detection systems are defined as security techniques that tend to detect individuals who are trying to sneak into a system without authorization. However, one technical challenge in intrusion detection systems is high rate of false positive alarms which affect their performance. To solve this problem, we propose an effective method, which can accurately find the correlation between network records. In this work, we compare the results using a linear measure and a nonlinear measure based on correlation coefficient and mutual information. Experiments on KDD Cup 99 data set show that our proposed method using the nonlinear correlation measure can not only reduce the rate of false alarms but also efficiently distinguish normal and abnormal behaviors, and provide higher detection and accuracy rate then using the linear correlation measure.

Medical physics, 2015

Electromagnetically guided endoscopic procedure, which aims at accurately and robustly localizing... more Electromagnetically guided endoscopic procedure, which aims at accurately and robustly localizing the endoscope, involves multimodal sensory information during interventions. However, it still remains challenging in how to integrate these information for precise and stable endoscopic guidance. To tackle such a challenge, this paper proposes a new framework on the basis of an enhanced particle swarm optimization method to effectively fuse these information for accurate and continuous endoscope localization. The authors use the particle swarm optimization method, which is one of stochastic evolutionary computation algorithms, to effectively fuse the multimodal information including preoperative information (i.e., computed tomography images) as a frame of reference, endoscopic camera videos, and positional sensor measurements (i.e., electromagnetic sensor outputs). Since the evolutionary computation method usually limits its possible premature convergence and evolutionary factors, the ...

Medical image analysis, Jan 17, 2015

This paper proposes an observation-driven adaptive differential evolution algorithm that fuses br... more This paper proposes an observation-driven adaptive differential evolution algorithm that fuses bronchoscopic video sequences, electromagnetic sensor measurements, and computed tomography images for accurate and smooth bronchoscope three-dimensional motion tracking. Currently an electromagnetic tracker with a position sensor fixed at the bronchoscope tip is commonly used to estimate bronchoscope movements. The large tracking error from directly using sensor measurements, which may be deteriorated heavily by patient respiratory motion and the magnetic field distortion of the tracker, limits clinical applications. How to effectively use sensor measurements for precise and stable bronchoscope electromagnetic tracking remains challenging. We here exploit an observation-driven adaptive differential evolution framework to address such a challenge and boost the tracking accuracy and smoothness. In our framework, two advantageous points are distinguished from other adaptive differential evol...

2012 IEEE International Conference on Multimedia and Expo, 2012

Recently, object tracking has been widely studied as a binary classification problem. Semi-superv... more Recently, object tracking has been widely studied as a binary classification problem. Semi-supervised learning is particularly suitable for improving classification accuracy when large quantities of unlabeled samples are generated (just like tracking procedure). The purpose of this paper is to fulfill robust and stable tracking by using collaborative learning, which belongs to the scope of semi-supervised learning, among three classifiers. Different from [1], random fern classifier is incorporated to deal with 2bitBP feature newly added and certain constraints are specially implemented in our framework. Besides, the way for selecting positive samples is also altered by us in order to achieve more stable tracking. Algorithm proposed in this paper is validated by tracking pedestrian and cup under occlusion. Experiments and comparison show that our algorithm can avoid drifting problem to some degree and make tracking result more robust and adaptive.

Enhancing Big Data Security with Collaborative Intrusion Detection

IEEE Cloud Computing, 2014

Lecture Notes in Computer Science, 2011

The quality of feature has significant impact on the performance of detection techniques used for... more The quality of feature has significant impact on the performance of detection techniques used for Denial-of-Service (DoS) attack. The features that fail to provide accurate characterization for network traffic records make the techniques suffer from low accuracy in detection. Although researches have been conducted and attempted to overcome this problem, there are some constraints in these works. In this paper, we propose a technique based on Euclidean Distance Map (EDM) for optimal feature extraction. The proposed technique runs analysis on original feature space (first-order statistics) and extracts the multivariate correlations between the first-order statistics. The extracted multivariate correlations, namely second-order statistics, preserve significant discriminative information for accurate characterizations of network traffic records, and these multivariate correlations can be the high-quality potential features for DoS attack detection. The effectiveness of the proposed technique is evaluated using KDD CUP 99 dataset and experimental analysis shows encouraging results.

International Journal of Internet Protocol Technology, 2014

(UTS), also a research member of Research Centre for Innovation in IT Services and Applications (... more (UTS), also a research member of Research Centre for Innovation in IT Services and Applications (iNEXT). His primary research interests include Computer and Network Security and on Pattern Recognition techniques for efficient Network Intrusion Detection and anomalous behavior detection.

2009 Fourth International Conference on Frontier of Computer Science and Technology, 2009

We propose a statistical model, namely Geometrical Structure Anomaly Detection (GSAD) to detect i... more We propose a statistical model, namely Geometrical Structure Anomaly Detection (GSAD) to detect intrusion using the packet payload in the network. GSAD takes into account the correlations among the packet payload features arranged in a geometrical structure. The representation is based on statistical analysis of Mahalanobis distances among payload features, which calculate the similarity of new data against precomputed profile. It calculates weight factor to determine anomaly in the payload. In the 1999 DARPA intrusion detection evaluation data set, we conduct several tests for limited attacks on port 80 and port 25. Our approach establishes and identifies the correlation among packet payloads in a network.

EURASIP Journal on Wireless Communications and Networking, 2012

One of the major objectives in multimedia research is to provide pervasive access and personalize... more One of the major objectives in multimedia research is to provide pervasive access and personalized use of multimedia information. Pervasive access of video data implies the access of cognitive and affective aspects of video content. Personalized use requires the services satisfy individual user's needs on video content. This article attempts to provide a content-on-demand (CoD) video adaptation solution by considering users' preference on cognitive content and affective content for video media in general, sports video and movies in particular. In this article, CoD video adaptation system is developed to support users' decision in selecting their content of interest and adaptively deliver video source by selecting relevant content and dropping frames while considering network conditions. First, video contents are annotated by the description schemes (DSs) provided by MPEG-7 multimedia description schemes (MDSs). Then, to achieve a generic adaptation solution, the adaptation is developed following MPEG-21 Digital Item Adaptation (DIA) framework. We study the MPEG-21 reference software on XML generation and develop our own system for CoD video adaptation in three steps: (1) the content information is parsed from MPEG-7 annotation XML file together with bitstream to generate generic Bitstream Syntax Description (gBSD); (2) Users' preference, network characteristic and adaptation QoS (AQoS) are considered for making adaptation decision; (3) adaptation engine automatically parses adaptation decisions and gBSD to achieve adaptation. Unlike most existing adaptation work, the system adapts the content of interest in the video stream according to users' preference. We implement the above-mentioned MPEG-7 and MPEG-21 standards and provide a generic video adaptation solution. Adaptation based on gBSD avoids complex video computation. Thirty students from various departments were invited to assess the system and their responses have been positive.

2011 18th IEEE International Conference on Image Processing, 2011

Movie shot classification is vital but challenging task due to various movie genres, different mo... more Movie shot classification is vital but challenging task due to various movie genres, different movie shooting techniques and much more shot types than other video domain. Variety of shot types are used in movies in order to attract audiences attention and enhance their watching experience. In this paper, we introduce context saliency to measure visual attention distributed in keyframes for movie shot classification. Different from traditional saliency maps, context saliency map is generated by removing redundancy from contrast saliency and incorporating geometry constrains. Context saliency is later combined with color and texture features to generate feature vectors. Support Vector Machine (SVM) is used to classify keyframes into pre-defined shot classes. Different from the existing works of either performing in a certain movie genre or classifying movie shot into limited directing semantic classes, the proposed method has three unique features: 1) context saliency significantly improves movie shot classification; 2) our method works for all movie genres; 3) our method deals with the most common types of video shots in movies. The experimental results indicate that the proposed method is effective and efficient for movie shot classification.

Lecture Notes in Computer Science, 2010

Computational cost is one of the major concerns of the commercial Intrusion Detection Systems (ID... more Computational cost is one of the major concerns of the commercial Intrusion Detection Systems (IDSs). Although these systems are proven to be promising in detecting network attacks, they need to check all the signatures to identify a suspicious attack in the worst case. This is time consuming. This paper proposes an efficient two-tier IDS, which applies a statistical signature approach and a Linear Discriminant Method (LDM) for the detection of various Web-based attacks. The two-tier system converts high-dimensional feature space into a low-dimensional feature space. It is able to reduce the computational cost and integrates groups of signatures into an identical signature. The integration of signatures reduces the cost of attack identification. The final decision is made on the integrated low-dimensional feature space. Finally, the proposed two-tier system is evaluated using DARPA 1999 IDS dataset for webbased attack detection.

Human behavior analysis is a hot topic in computer vision and is applied widely in many applicati... more Human behavior analysis is a hot topic in computer vision and is applied widely in many applications. Human behavior retrieval is another frontier technology in the area of multimedia information retrieval, which is related to human behavior analysis but holds several differences because of its special application purpose. Human behaviour retrieval to some extent is similar to human behaviour analysis, but the technology used for human behavior analysis cannot be used for human behavior directly. This paper will address such kind of differences and review several technologies including video retrieval, feature extraction, similarity measure and human behavior analysis.