Browsing by Author "Xu W"

Now showing 1 - 8 of 8
  • Thumbnail Image
    Item
    AE-MLP: A Hybrid Deep Learning Approach for DDoS Detection and Classification
    (IEEE, 2021-10-27) Wei Y; Jang-Jaccard J; Sabrina F; Singh A; Xu W; Camtepe S; Oliva D
    Distributed Denial-of-Service (DDoS) attacks are increasing as the demand for Internet connectivity massively grows in recent years. Conventional shallow machine learning-based techniques for DDoS attack classification tend to be ineffective when the volume and features of network traffic, potentially carry malicious DDoS payloads, increase exponentially as they cannot extract high importance features automatically. To address this concern, we propose a hybrid approach named AE-MLP that combines two deep learning-based models for effective DDoS attack detection and classification. The Autoencoder (AE) part of our proposed model provides an effective feature extraction that finds the most relevant feature sets automatically without human intervention (e.g., knowledge of cybersecurity professionals). The Multi-layer Perceptron Network (MLP) part of our proposed model uses the compressed and reduced feature sets produced by the AE as inputs and classifies the attacks into different DDoS attack types to overcome the performance overhead and bias associated with processing large feature sets with noise (i.e., unnecessary feature values). Our experimental results, obtained through comprehensive and extensive experiments on different aspects of performance on the CICDDoS2019 dataset, demonstrate both a very high and robust accuracy rate and F1-score that exceed 98% which also outperformed the performance of many similar methods. This shows that our proposed model can be used as an effective DDoS defense tool against the growing number of DDoS attacks.
  • Thumbnail Image
    Item
    An improved MTT colorimetric method for rapid viable bacteria counting
    (Elsevier BV, 2023-11) Xu W; Shi D; Chen K; Palmer J; Popovich DG
    The 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyl tetrazolium bromide (MTT) assay has been employed in the analysis of bacterial growth. In comparison to experiments conducted on mammalian cells, the MTT bacterial assay encounters a greater number of interfering factors and obstacles that impact the accuracy of results. In this study, we have elucidated an improved MTT assay protocol and put forth an equation that establishes a correlation between colony-forming units (CFU) and the amount of formazan converted by the bacteria, drawing upon the fundamental principle of the MTT assay. This equation is represented as CFU=kF. Furthermore, we have explicated a methodology to determine the scale factor "k" by employing S. aureus and E. coli as illustrative examples. The findings indicate that S. aureus and E. coli reduce MTT by a cyclic process, from which the optimal reduction time at room temperature was determined to be approximately 30 mins. Furthermore, individual E. coli exhibits an MTT reduction capacity approximately four times greater than that of S. aureus. HPLC analysis proves to be the most accurate method for mitigating interferences during the dissolution and quantification of formazan. Additionally, this study has identified a new constraint related to the narrow linear range (0-125 μg/mL) of formazan concentration-absorbance and has presented strategies to circumvent this limitation.
  • Thumbnail Image
    Item
    An Investigation about Gene Modules Associated with hDPSC Differentiation for Adolescents
    (Hindawi Limited, 2019-04-04) Xu W; Li J; Li J; Yang J-J; Wang Q; Liu B; Qiu W; Ballini A
    Dental pulp stem cells (DPSCs) have the property of self-renewal and multidirectional differentiation so that they have the potential for future regenerative therapy of various diseases. The latest breakthrough in the biology of stem cells and the development of regenerative biology provides an effective strategy for regenerative therapy. However, in the medium promoting differentiation during long-term passage, DPSCs would lose their differentiation capability. Some efforts have been made to find genes influencing human DPSC (hDPSC) differentiation based on hDPSCs isolated from adults. However, hDPSC differentiation is a very complex process, which involves multiple genes and multielement interactions. The purpose of this study is to detect sets of correlated genes (i.e., gene modules) that are associated to hDPSC differentiation at the crown-completed stage of the third molars, by using weighted gene coexpression network analysis (WGCNA). Based on the gene expression dataset GSE10444 from Gene Expression Omnibus (GEO), we identified two significant gene modules: yellow module (742 genes) and salmon module (9 genes). The WEB-based Gene SeT AnaLysis Toolkit showed that the 742 genes in the yellow module were enriched in 59 KEGG pathways (including Wnt signaling pathway), while the 9 genes in the salmon module were enriched in one KEGG pathway (neurotrophin signaling pathway). There were 660 (7) genes upregulated at P10 and 82 (2) genes downregulated at P10 in the yellow (salmon) module. Our results provide new insights into the differentiation capability of hDPSCs.
  • Thumbnail Image
    Item
    Artificial 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 Y
    A 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.
  • Thumbnail Image
    Item
    Hedgehogs as Amplifying Hosts of Severe Fever with Thrombocytopenia Syndrome Virus, China.
    (2022-12) Zhao C; Zhang X; Si X; Ye L; Lawrence K; Lu Y; Du C; Xu H; Yang Q; Xia Q; Yu G; Xu W; Yuan F; Hao J; Jiang J-F; Zheng A
    Severe fever with thrombocytopenia syndrome virus (SFTSV) is a tickborne bandavirus mainly transmitted by Haemaphysalis longicornis ticks in East Asia, mostly in rural areas. As of April 2022, the amplifying host involved in the natural transmission of SFTSV remained unidentified. Our epidemiologic field survey conducted in endemic areas in China showed that hedgehogs were widely distributed, had heavy tick infestations, and had high SFTSV seroprevalence and RNA prevalence. After experimental infection of Erinaceus amurensis and Atelerix albiventris hedgehogs with SFTSV, we detected robust but transitory viremias that lasted for 9-11 days. We completed the SFTSV transmission cycle between hedgehogs and nymph and adult H. longicornis ticks under laboratory conditions with 100% efficiency. Furthermore, naive H. longicornis ticks could be infected by SFTSV-positive ticks co-feeding on naive hedgehogs; we confirmed transstadial transmission of SFTSV. Our study suggests that the hedgehogs are a notable wildlife amplifying host of SFTSV in China.
  • Thumbnail Image
    Item
    Improved 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 J
    Existing 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.
  • Thumbnail Image
    Item
    Improving Performance of Autoencoder-Based Network Anomaly Detection on NSL-KDD Dataset
    (IEEE, 2021-09-29) Xu W; Jang-Jaccard J; Singh A; Wei Y; Sabrina F; Ji Z
    Network anomaly detection plays a crucial role as it provides an effective mechanism to block or stop cyberattacks. With the recent advancement of Artificial Intelligence (AI), there has been a number of Autoencoder (AE) based deep learning approaches for network anomaly detection to improve our posture towards network security. The performance of existing state-of-the-art AE models used for network anomaly detection varies without offering a holistic approach to understand the critical impacts of the core set of important performance indicators of AE models and the detection accuracy. In this study, we propose a novel 5-layer autoencoder (AE)-based model better suited for network anomaly detection tasks. Our proposal is based on the results we obtained through an extensive and rigorous investigation of several performance indicators involved in an AE model. In our proposed model, we use a new data pre-processing methodology that transforms and removes the most affected outliers from the input samples to reduce model bias caused by data imbalance across different data types in the feature set. Our proposed model utilizes the most effective reconstruction error function which plays an essential role for the model to decide whether a network traffic sample is normal or anomalous. These sets of innovative approaches and the optimal model architecture allow our model to be better equipped for feature learning and dimension reduction thus producing better detection accuracy as well as f1-score. We evaluated our proposed model on the NSL-KDD dataset which outperformed other similar methods by achieving the highest accuracy and f1-score at 90.61% and 92.26% respectively in detection.
  • Thumbnail Image
    Item
    Pharmacokinetic Properties of Baitouweng Decoction in Bama Miniature Pigs: Implications for Clinical Application in Humans
    (Hindawi, 2024-05-10) Xu Q; Gao H; Zhu F; Xu W; Wang Y; Xie J; Guo G; Yang L; Ma L; Shen Z; Li J; Regmi B
    Traditional Chinese medicine (TCM) serves as a significant adjunct to chemical treatment for chronic diseases. For instance, the administration of Baitouweng decoction (BTWD) has proven effective in the treatment of ulcerative colitis. However, the limited understanding of its pharmacokinetics (PK) has impeded its widespread use. Chinese Bama miniature pigs possess anatomical and physiological similarities to the human body, making them a valuable model for investigating PK properties. Consequently, the identification of PK properties in Bama miniature pigs can provide valuable insights for guiding the clinical application of BTWD in humans. To facilitate this research, a rapid and sensitive UPLC-MS/MS method has been developed for the simultaneous quantification of eleven active ingredients of BTWD in plasma. Chromatographic separation was conducted using an Acquity UPLC HSS T3 C18 column and a gradient mobile phase comprising acetonitrile and water (containing 0.1% acetic acid). The methodology was validated in accordance with the FDA Bioanalytical Method Validation Guidance for Industry. The lower limit of quantitation fell within the range of 0.60-2.01 ng/mL. Pharmacokinetic studies indicated that coptisine chloride, berberine, columbamine, phellodendrine, and obacunone exhibited low Cmax, while fraxetin, esculin, fraxin, and pulchinenoside B4 were rapidly absorbed and eliminated from the plasma. These findings have implications for the development of effective components in BTWD and the adjustment of clinical dosage regimens.