Bo Luo

Security research has concentrated on converting operating system audit logs into suitable graphs, such as provenance graphs, for analysis. However, provenance graphs can grow very large requiring significant computational resources beyond what is necessary for many security tasks and are not feasible for resource constrained environments, such as edge devices. To address this problem, we present the \textit{resource-interaction graph} that is built directly from the audit log. We show that the resource-interaction graph's storage requirements are significantly lower than provenance graphs using an open-source data set with two container escape attacks captured from an edge device. We use a graph autoencoder and graph clustering technique to evaluate the representation for an anomaly detection task. Both approaches are unsupervised and are thus suitable for detecting zero-day attacks. The approaches can achieve f1 scores typically over 80\% and in some cases over 90\% for the selected data set and attacks.

Tool condition monitoring is critical in ultra-precision manufacturing in order to optimize the performance of the overall process, while maintaining the desired part quality. Recently, Deep Learning has been successfully applied in numerous classification tasks in manufacturing, often to forecast part quality. In this paper, a novel Deep Learning data-driven modeling framework is presented, which includes fusion of multiple stacked sparse autoencoders for tool condition monitoring in ultra-precision machining. The proposed computational framework consists of two main structures. A training model that is designed with the ability to process multiple parallel feature spaces to learn the lower-level features; and a feature fusion structure that is used to learn the higher-level features and associations to tool wear. To achieve this learning structure, a modified loss function is utilized that enhances the feature extraction and classification tasks. A dataset from a real manufacturing process is used to demonstrate the performance of the proposed framework. Experimental results and simulations show that the proposed method successfully classifies the ultra-precision machining case study with over 96% accuracy, while also outperforms comparable methodologies.

In modern digital manufacturing, nearly 79.6% of the downtime of a machine tool is caused by its mechanical failures. Predictive maintenance (PdM) is a useful way to minimize the machine downtime and the associated costs. One of the challenges with PdM is early fault detection under time-varying operational conditions, which means mining sensitive fault features from condition signals in long-term running. However, fault features are often weakened and disturbed by the time-varying harmonics and noise during a machining process. Existing analysis methods of these complex and diverse data are inefficient and time-consuming. This paper proposes a novel method for early fault detection under time-varying conditions. In this study, a deep learning model is constructed to automatically select the impulse responses from the vibration signals in long-term running of 288 days. Then, dynamic properties are identified from the selected impulse responses to detect the early mechanical fault under time-varying conditions. Compared to traditional methods, the experimental results in this paper have proved that our method was not affected by time-varying conditions and showed considerable potential for early fault detection in manufacturing.

Prostate cancer (PCa) is a major cause of death since ancient time documented in Egyptian Ptolemaic mummy imaging. PCa detection is critical to personalized medicine and varies considerably under an MRI scan. 172 patients with 2,602 morphologic images (axial 2D T2-weighted imaging) of the prostate were obtained. A deep learning with deep convolutional neural network (DCNN) and a non-deep learning with SIFT image feature and bag-of-word (BoW), a representative method for image recognition and analysis, were used to distinguish pathologically confirmed PCa patients from prostate benign conditions (BCs) patients with prostatitis or prostate benign hyperplasia (BPH). In fully automated detection of PCa patients, deep learning had a statistically higher area under the receiver operating characteristics curve (AUC) than non-deep learning (P = 0.0007 < 0.001). The AUCs were 0.84 (95% CI 0.78–0.89) for deep learning method and 0.70 (95% CI 0.63–0.77) for non-deep learning method, respectively. Our results suggest that deep learning with DCNN is superior to non-deep learning with SIFT image feature and BoW model for fully automated PCa patients differentiation from prostate BCs patients. Our deep learning method is extensible to image modalities such as MR imaging, CT and PET of other organs.

Heavy machine tool work under such high-load conditions that chatter vibrations are prone to occur, which significantly diminishes the machining efficiency and quality. Stability lobe diagrams are commonly used to select appropriate spindle speed and axial depth of cut to get rid of chatter and maximize the material removal rate. However, this needs precise identification of the dynamics of the entire machine tool structure, especially in the low-frequency range. Operational modal analysis has been the proven technique for estimating dynamic characteristics of machine tool structures in operation conditions. In this article, a complete methodology was presented for employing operational modal analysis for heavy machine tool in machining conditions. A random cutting exciting method originally presented by Minis is modified which generates pseudorandom impulse force to excite a heavy vertical lathe structure. And the excitation signal of random cutting force was modeled to analyze the effect of cutting parameters on energy and frequency band of the excitation. One operational modal analysis method, the pLSCF (referred to as PolyMAX) method, was employed to estimate modal parameters during machining. It was also observed in chatter tests that the operational modal analysis results are more accurate than the traditional impact test results in characterizing the dynamics of machine tool structure in machining.