Browsing by Author "Liu T"
Now showing 1 - 11 of 11
Results Per Page
Sort Options
- ItemArtificial Intelligence-Enabled DDoS Detection for Blockchain-Based Smart Transport Systems.(MDPI (Basel, Switzerland), 2021-12-22) Liu T; Sabrina F; Jang-Jaccard J; Xu W; Wei YA smart public transport system is expected to be an integral part of our human lives to improve our mobility and reduce the effect of our carbon footprint. The safety and ongoing maintenance of the smart public transport system from cyberattacks are vitally important. To provide more comprehensive protection against potential cyberattacks, we propose a novel approach that combines blockchain technology and a deep learning method that can better protect the smart public transport system. By the creation of signed and verified blockchain blocks and chaining of hashed blocks, the blockchain in our proposal can withstand unauthorized integrity attack that tries to forge sensitive transport maintenance data and transactions associated with it. A hybrid deep learning-based method, which combines autoencoder (AE) and multi-layer perceptron (MLP), in our proposal can effectively detect distributed denial of service (DDoS) attempts that can halt or block the urgent and critical exchange of transport maintenance data across the stakeholders. The experimental results of the hybrid deep learning evaluated on three different datasets (i.e., CICDDoS2019, CIC-IDS2017, and BoT-IoT) show that our deep learning model is effective to detect a wide range of DDoS attacks achieving more than 95% F1-score across all three datasets in average. The comparison of our approach with other similar methods confirms that our approach covers a more comprehensive range of security properties for the smart public transport system.
- ItemCompleted sample correlations and feature dependency-based unsupervised feature selection(Springer Science+Business Media, LLC, 2023-04) Liu T; Hu R; Zhu YSample correlations and feature relations are two pieces of information that are needed to be considered in the unsupervised feature selection, as labels are missing to guide model construction. Thus, we design a novel unsupervised feature selection scheme, in this paper, via considering the completed sample correlations and feature dependencies in a unified framework. Specifically, self-representation dependencies and graph construction are conducted to preserve and select the important neighbors for each sample in a comprehensive way. Besides, mutual information and sparse learning are designed to consider the correlations between features and to remove the informative features, respectively. Moreover, various constraints are constructed to automatically obtain the number of important neighbors and to conduct graph partition for the clustering task. Finally, we test the proposed method and verify the effectiveness and the robustness on eight data sets, comparing with nine state-of-the-art approaches with regard to three evaluation metrics for the clustering task.
- ItemImproved Bidirectional GAN-Based Approach for Network Intrusion Detection Using One-Class Classifier(MDPI (Basel, Switzerland), 2022-06-01) Xu W; Jang-Jaccard J; Liu T; Sabrina F; Kwak JExisting generative adversarial networks (GANs), primarily used for creating fake image samples from natural images, demand a strong dependence (i.e., the training strategy of the generators and the discriminators require to be in sync) for the generators to produce as realistic fake samples that can “fool” the discriminators. We argue that this strong dependency required for GAN training on images does not necessarily work for GAN models for network intrusion detection tasks. This is because the network intrusion inputs have a simpler feature structure such as relatively low-dimension, discrete feature values, and smaller input size compared to the existing GAN-based anomaly detection tasks proposed on images. To address this issue, we propose a new Bidirectional GAN (Bi-GAN) model that is better equipped for network intrusion detection with reduced overheads involved in excessive training. In our proposed method, the training iteration of the generator (and accordingly the encoder) is increased separate from the training of the discriminator until it satisfies the condition associated with the cross-entropy loss. Our empirical results show that this proposed training strategy greatly improves the performance of both the generator and the discriminator even in the presence of imbalanced classes. In addition, our model offers a new construct of a one-class classifier using the trained encoder–discriminator. The one-class classifier detects anomalous network traffic based on binary classification results instead of calculating expensive and complex anomaly scores (or thresholds). Our experimental result illustrates that our proposed method is highly effective to be used in network intrusion detection tasks and outperforms other similar generative methods on two datasets: NSL-KDD and CIC-DDoS2019 datasets.
- ItemInitialization-similarity clustering algorithm(Springer Science+Business Media, LLC, 2019-12) Liu T; Zhu J; Zhou J; Zhu Y; Zhu XClassic k-means clustering algorithm randomly selects centroids for initialization to possibly output unstable clustering results. Moreover, random initialization makes the clustering result hard to reproduce. Spectral clustering algorithm is a two-step strategy, which first generates a similarity matrix and then conducts eigenvalue decomposition on the Laplacian matrix of the similarity matrix to obtain the spectral representation. However, the goal of the first step in the spectral clustering algorithm does not guarantee the best clustering result. To address the above issues, this paper proposes an Initialization-Similarity (IS) algorithm which learns the similarity matrix and the new representation in a unified way and fixes initialization using the sum-of-norms regularization to make the clustering more robust. The experimental results on ten real-world benchmark datasets demonstrate that our IS clustering algorithm outperforms the comparison clustering algorithms in terms of three evaluation metrics for clustering algorithm including accuracy (ACC), normalized mutual information (NMI), and Purity.
- ItemJoint Spectral Clustering based on Optimal Graph and Feature Selection(Springer Nature Switzerland AG, 2021-02) Zhu J; Jang-Jaccard J; Liu T; Zhou JRedundant features and outliers (noise) included in the data points for a machine learning clustering model heavily influences the discovery of more distinguished features for clustering. To solve this issue, we propose a spectral new clustering method to consider the feature selection with the L2 , 1-norm regularization as well as simultaneously learns orthogonal representations for each sample to preserve the local structures of data points. Our model also solves the issue of out-of-sample, where the training process does not output an explicit model to predict unseen data points, along with providing an efficient optimization method for the proposed objective function. Experimental results showed that our method on twelve data sets achieves the best performance compared with other similar models.
- ItemMulti-task multi-modality SVM for early COVID-19 Diagnosis using chest CT data.(Elsevier Ltd, 2022-01) Hu R; Gan J; Zhu X; Liu T; Shi XIn the early diagnosis of the Coronavirus disease (COVID-19), it is of great importance for either distinguishing severe cases from mild cases or predicting the conversion time that mild cases would possibly convert to severe cases. This study investigates both of them in a unified framework by exploring the problems such as slight appearance difference between mild cases and severe cases, the interpretability, the High Dimension and Low Sample Size (HDLSS) data, and the class imbalance. To this end, the proposed framework includes three steps: (1) feature extraction which first conducts the hierarchical segmentation on the chest Computed Tomography (CT) image data and then extracts multi-modality handcrafted features for each segment, aiming at capturing the slight appearance difference from different perspectives; (2) data augmentation which employs the over-sampling technique to augment the number of samples corresponding to the minority classes, aiming at investigating the class imbalance problem; and (3) joint construction of classification and regression by proposing a novel Multi-task Multi-modality Support Vector Machine (MM-SVM) method to solve the issue of the HDLSS data and achieve the interpretability. Experimental analysis on two synthetic and one real COVID-19 data set demonstrated that our proposed framework outperformed six state-of-the-art methods in terms of binary classification and regression performance.
- ItemNon-negative Matrix Factorization: A Survey(Oxford University Press on behalf of the British Computer Society, 2021-07-01) Gan J; Liu T; Li L; Zhang JNon-negative matrix factorization (NMF) is a powerful tool for data science researchers, and it has been successfully applied to data mining and machine learning community, due to its advantages such as simple form, good interpretability and less storage space. In this paper, we give a detailed survey on existing NMF methods, including a comprehensive analysis of their design principles, characteristics and drawbacks. In addition, we also discuss various variants of NMF methods and analyse properties and applications of these variants. Finally, we evaluate the performance of nine NMF methods through numerical experiments, and the results show that NMF methods perform well in clustering tasks.
- ItemParameter-Free Extreme Learning Machine for Imbalanced Classification Authors Li, L - China Agric(Springer Science+Business Media, LLC, 2020-12) Li L; Zhao K; Sun R; Gan J; Yuan G; Liu TImbalanced data distribution is a common problem in classification situations, that is the number of samples in different categories varies greatly, thus increasing the classification difficulty. Although many methods have been used for the imbalanced data classification, there are still problems with low classification accuracy in minority class and adding additional parameter settings. In order to increase minority classification accuracy in imbalanced problem, this paper proposes a parameter-free weighting learning mechanism based on extreme learning machine and sample loss values to balance the number of samples in each training step. The proposed method mainly includes two aspects: the sample weight learning process based on the sample losses; the sample selection process and weight update process according to the constraint function and iterations. Experimental results on twelve datasets from the KEEL repository show that the proposed method could achieve more balanced and accurate results than other compared methods in this work.
- ItemThe perceived benefits of apps by construction professionals in New Zealand(MDPI AG, 2017-12-01) Liu T; Mbachu J; Mathrani A; Jones B; McDonald BThe construction sector is a key driver of economic growth in New Zealand; however, its productivity is still considered to be low. Prior research has suggested that information and communication technology (ICT) can help enhance efficiency and productivity. However, there is little research on the use of mobile technologies by New Zealand construction workforce. This paper reports findings of an exploratory study with the objective of examining the perceived benefits regarding uptake of apps in New Zealand construction sector. Using self-administered questionnaire survey, feedback was received from the major construction trade and professional organisations in New Zealand. Survey data was analyzed using descriptive, one-sample t-test, Spearman’s rank correlation coefficient and structural equation modeling. Results showed that iPhone and Android phone currently dominate the smartphone market in New Zealand construction industry. The top three application areas are site photos, health and safety reporting and timekeeping. The benefits of mobile apps were widely confirmed by the construction professionals. The benefit of “better client relationship management and satisfaction” has substantial correlation with overall productivity improvement and best predictor of the overall productivity improvement. These findings provide a starting point for further research aimed at improving the uptake and full leveraging of mobile technologies to improve the dwindling productivity trend in New Zealand construction industry.
- ItemTransnational physical activity and sport engagement of new Asian migrants in Aotearoa/New Zealand(Victoria University of Wellington and John Wiley and Sons Australia Ltd, 2022-08) Liu T; Liu LSBased upon a literature review, this paper first identifies and articulates the importance of studying physical activity and sport (PAS) engagement of new Asian migrants within a particular geographical location – New Zealand. A pilot study with a series of in-depth interviews highlights some challenges that New Zealand Regional Sports Organisations (RSOs) and new Asian migrants face in terms of PAS engagement. Findings from the pilot study interviews indicate that RSOs in New Zealand are well aware of these challenges, and these challenges mainly stem from a lack of understanding of the needs of new Asian migrant communities. These findings also indicate that ethnicity plays a significant role in influencing migrants' PAS engagement.
- ItemWeighted adjacent matrix for K-means clustering(Springer Science+Business Media, LLC, 2019-12) Zhou J; Liu T; Zhu JK-means clustering is one of the most popular clustering algorithms and has been embedded in other clustering algorithms, e.g. the last step of spectral clustering. In this paper, we propose two techniques to improve previous k-means clustering algorithm by designing two different adjacent matrices. Extensive experiments on public UCI datasets showed the clustering results of our proposed algorithms significantly outperform three classical clustering algorithms in terms of different evaluation metrics.