A Framework for Detecting System Performance Anomalies Using Tracing Data Analysis

Advances in technology and computing power have led to the emergence of complex and large-scale software architectures in recent years. However, they are prone to performance anomalies due to various reasons, including software bugs, hardware failures, and resource contentions. Performance metrics represent the average load on the system and do not help discover the cause of the problem if abnormal behavior occurs during software execution. Consequently, system experts have to examine a massive amount of low-level tracing data to determine the cause of a performance issue. In this work, we propose an anomaly detection framework that reduces troubleshooting time, besides guiding developers to discover performance problems by highlighting anomalous parts in trace data. Our framework works by collecting streams of system calls during the execution of a process using the Linux Trace Toolkit Next Generation(LTTng), sending them to a machine learning module that reveals anomalous subsequences of system calls based on their execution times and frequency. Extensive experiments on real datasets from two different applications (e.g., MySQL and Chrome), for varying scenarios in terms of available labeled data, demonstrate the effectiveness of our approach to distinguish normal sequences from abnormal ones.     

Ensemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection

Multivariate time series anomaly detection is a widespread problem in the field of failure prevention. Fast prevention means lower repair costs and losses. The amount of sensors in novel industry systems makes the anomaly detection process quite difficult for humans. Algorithms that automate the process of detecting anomalies are crucial in modern failure prevention systems. Therefore, many machine learning models have been designed to address this problem. Mostly, they are autoencoder-based architectures with some generative adversarial elements. This work shows a framework that incorporates neuroevolution methods to boost the anomaly detection scores of new and already known models. The presented approach adapts evolution strategies for evolving an ensemble model, in which every single model works on a subgroup of data sensors. The next goal of neuroevolution is to optimize the architecture and hyperparameters such as the window size, the number of layers, and the layer depths. The proposed framework shows that it is possible to boost most anomaly detection deep learning models in a reasonable time and a fully automated mode. We ran tests on the SWAT and WADI datasets. To the best of our knowledge, this is the first approach in which an ensemble deep learning anomaly detection model is built in a fully automatic way using a neuroevolution strategy.     

Application of Improved Asynchronous Advantage Actor Critic Reinforcement Learning Model on Anomaly Detection

Anomaly detection research was conducted traditionally using mathematical and statistical methods. This topic has been widely applied in many fields. Recently reinforcement learning has achieved exceptional successes in many areas such as the AlphaGo chess playing and video gaming etc. However, there were scarce researches applying reinforcement learning to the field of anomaly detection. This paper therefore aimed at proposing an adaptable asynchronous advantage actor-critic model of reinforcement learning to this field. The performances were evaluated and compared among classical machine learning and the generative adversarial model with variants. Basic principles of the related models were introduced firstly. Then problem definitions, modelling processes and testing were detailed. The proposed model differentiated the sequence and image from other anomalies by proposing appropriate neural networks of attention mechanism and convolutional network for the two kinds of anomalies, respectively. Finally, performances with classical models using public benchmark datasets (NSL-KDD, AWID and CICIDS-2017, DoHBrw-2020) were evaluated and compared. Experiments confirmed the effectiveness of the proposed model with the results indicating higher rewards and lower loss rates on the datasets during training and testing. The metrics of precision, recall rate and F1 score were higher than or at least comparable to the state-of-the-art models. We concluded the proposed model could outperform or at least achieve comparable results with the existing anomaly detection models.     

A New Deep Dual Temporal Domain Adaptation Method for Online Detection of Bearings Early Fault

With the quick development of sensor technology in recent years, online detection of early fault without system halt has received much attention in the field of bearing prognostics and health management. While lacking representative samples of the online data, one can try to adapt the previously-learned detection rule to the online detection task instead of training a new rule merely using online data. As one may come across a change of the data distribution between offline and online working conditions, it is challenging to utilize the data from different working conditions to improve detection accuracy and robustness. To solve this problem, a new online detection method of bearing early fault is proposed in this paper based on deep transfer learning. The proposed method contains an offline stage and an online stage. In the offline stage, a new state assessment method is proposed to determine the period of the normal state and the degradation state for whole-life degradation sequences. Moreover, a new deep dual temporal domain adaptation (DTDA) model is proposed. By adopting a dual adaptation strategy on the time convolutional network and domain adversarial neural network, the DTDA model can effectively extract domain-invariant temporal feature representation. In the online stage, each sequentially-arrived data batch is directly fed into the trained DTDA model to recognize whether an early fault occurs. Furthermore, a health indicator of target bearing is also built based on the DTDA features to intuitively evaluate the detection results. Experiments are conducted on the IEEE Prognostics and Health Management (PHM) Challenge 2012 bearing dataset. The results show that, compared with nine state-of-the-art fault detection and diagnosis methods, the proposed method can get an earlier detection location and lower false alarm rate.     

面向近红外光谱定量分析的深度学习建模与模型迁移

近红外光谱分析技术依赖于表征光谱向量和预测目标之间关系的化学计量学方法。然而，样品的光谱由信号和各种噪声组成，传统化学计量学方法较难直接提取光谱的有效特征，并为复杂的预测任务建立具有较强泛用性的校正模型。进一步地，受限于仪器间的差异，在一台仪器上建立的模型应用于另一台仪器时，难以取得相同的定量分析结果。为此，提出了一种基于卷积神经网络和迁移学习的定量分析建模及模型传递方案，以提高模型在单仪器和跨仪器上的预测性能。在卷积神经网络的基础上，一种结合多尺度特征融合和残差结构，名为MSRCNN的先进模型被设计，并在主仪器上展现了卓越的预测能力。然后，设计了四种的基于fine-tune模型迁移策略，将在主仪器上建立的MSRCNN模型迁移到从仪器。在药品和小麦的公开数据集上的实验结果表明，MSRCNN在主仪器上的RMSE和R2分别为2.587，0.981和0.309，0.977，优于PLS，SVM和CNN。在利用30个从仪器的样本微调主仪器建立的模型后，迁移MSRCNN中的卷积层和全连接层的方案取得了最好效果，其RMSE和R2可分别达到2.289，0.982和0.379，0.965。增加参与模型微调的从仪器样本，可进一步提高性能。     

An interpretable intrusion detection method based on few-shot learning in cloud-ground interconnection

An enterprise’s private cloud may be attacked by attackers when communicating with the public cloud. Although traffic detection methods based on deep learning have been widely used, these methods rely on a large amount of sample data and cannot quickly detect new attacks such as Zero-day Attacks. Moreover, deep learning has a black-box nature and cannot interpret the detection results, which has certain security risks. This paper proposes an interpretable abnormal traffic detection method, which can complete the detection task with only a few malicious traffic samples. Specifically, it uses the covariance matrix to characterize each traffic category and then calculates the similarity between the query traffic and each category according to the covariance metric function to realize the traffic detection based on few-shot learning. After that, the traffic images processed by the random masks are input into the model to obtain the predicted probability of the corresponding traffic category. Finally, the predicted probability is linearly summed with each mask to generate the final saliency map to interpret and analyze the model decision. In this paper, experiments are carried out by simulating only 15 and 25 malicious traffic samples. The results show that the proposed method can obtain good accuracy and recall, and the interpretation analysis shows that the model is reliable and interpretable.     

深度复卷积递归网络模型的师生学习语声增强方法

基于深度神经网络的方法已经在语声增强领域得到了广泛的应用,然而若想取得理想的性能,一般需要规模较大且复杂度较高的模型。因此,在计算资源有限的设备或对延时要求高的环境下容易出现部署困难的问题。为了解决此问题,提出了一种基于深度复卷积递归网络的师生学习语声增强方法。在师生深度复卷积递归网络模型结构中间的复长短时记忆递归模块提取实部和虚部特征流,并分别计算帧级师生距离损失以进行知识转移。同时使用多分辨率频谱损失以进一步提升低复杂度学生模型的性能。实验在公开数据集Voice Bank Demand和DNS Challenge上进行,结果显示所提方法相对于基线学生模型在各项指标上均有明显提升。     

KnowRU: Knowledge Reuse via Knowledge Distillation in Multi-Agent Reinforcement Learning

Recently, deep reinforcement learning (RL) algorithms have achieved significant progress in the multi-agent domain. However, training for increasingly complex tasks would be time-consuming and resource intensive. To alleviate this problem, efficient leveraging of historical experience is essential, which is under-explored in previous studies because most existing methods fail to achieve this goal in a continuously dynamic system owing to their complicated design. In this paper, we propose a method for knowledge reuse called “KnowRU”, which can be easily deployed in the majority of multi-agent reinforcement learning (MARL) algorithms without requiring complicated hand-coded design. We employ the knowledge distillation paradigm to transfer knowledge among agents to shorten the training phase for new tasks while improving the asymptotic performance of agents. To empirically demonstrate the robustness and effectiveness of KnowRU, we perform extensive experiments on state-of-the-art MARL algorithms in collaborative and competitive scenarios. The results show that KnowRU outperforms recently reported methods and not only successfully accelerates the training phase, but also improves the training performance, emphasizing the importance of the proposed knowledge reuse for MARL.     

基于监督学习的紫外-可见光光谱水质在线异常检测方法研究

水资源关系到国计民生,近年来时有发生的水污染事件使污染物入侵预警得到了广泛的社会关注。针对现有基于紫外-可见光光谱的水质异常检测方法存在的检出下限偏低的问题,提出一种基于监督学习的紫外-可见光光谱水质异常检测方法。该方法首先获取不同数据集中的正常样本差异性空间,再使用正交投影方法去除差异性空间中的光谱数据分量,以达到基线校正的目的;然后采用偏最小二乘判别分析从校正后的光谱中提取特征,利用训练集得到的最优阈值确定离群点;最后采用序贯贝叶斯滚动更新每个时刻上的异常概率,确定水质报警序列。实验选用苯酚作为模拟污染入侵事件的注入试剂,采样2周内的紫外-可见光光谱数据,在实验平台上对提出的方法进行了验证。实验结果表明,采用的正交投影基线校正方法可以消除不同批次水质光谱的背景差异,更为充分的利用了光谱信息,降低了对特征污染物的检出下限。     

Crash Diagnosis and Price Rebound Prediction in NYSE Composite Index Based on Visibility Graph and Time-Evolving Stock Correlation Network

This study proposes a framework to diagnose stock market crashes and predict the subsequent price rebounds. Based on the observation of anomalous changes in stock correlation networks during market crashes, we extend the log-periodic power-law model with a metric that is proposed to measure network anomalies. To calculate this metric, we design a prediction-guided anomaly detection algorithm based on the extreme value theory. Finally, we proposed a hybrid indicator to predict price rebounds of the stock index by combining the network anomaly metric and the visibility graph-based log-periodic power-law model. Experiments are conducted based on the New York Stock Exchange Composite Index from 4 January 1991 to 7 May 2021. It is shown that our proposed method outperforms the benchmark log-periodic power-law model on detecting the 12 major crashes and predicting the subsequent price rebounds by reducing the false alarm rate. This study sheds light on combining stock network analysis and financial time series modeling and highlights that anomalous changes of a stock network can be important criteria for detecting crashes and predicting recoveries of the stock market.     

Research on the Fastest Detection Method for Weak Trends under Noise Interference

Trend anomaly detection is the practice of comparing and analyzing current and historical data trends to detect real-time abnormalities in online industrial data-streams. It has the advantages of tracking a concept drift automatically and predicting trend changes in the shortest time, making it important both for algorithmic research and industry. However, industrial data streams contain considerable noise that interferes with detecting weak anomalies. In this paper, the fastest detection algorithm “sliding nesting” is adopted. It is based on calculating the data weight in each window by applying variable weights, while maintaining the method of trend-effective integration accumulation. The new algorithm changes the traditional calculation method of the trend anomaly detection score, which calculates the score in a short window. This algorithm, SNWFD–DS, can detect weak trend abnormalities in the presence of noise interference. Compared with other methods, it has significant advantages. An on-site oil drilling data test shows that this method can significantly reduce delays compared with other methods and can improve the detection accuracy of weak trend anomalies under noise interference.     

Investigation on Identifying Implicit Learning Event from EEG Signal Using Multiscale Entropy and Artificial Bee Colony

The way people learn will play an essential role in the sustainable development of the educational system for the future. Utilizing technology in the age of information and incorporating it into how people learn can produce better learners. Implicit learning is a type of learning of the underlying rules without consciously seeking or understanding the rules; it is commonly seen in small children while learning how to speak their native language without learning grammar. This research aims to introduce a processing system that can systematically identify the relationship between implicit learning events and their Encephalogram (EEG) signal characteristics. This study converted the EEG signal from participants while performing cognitive task experiments into Multiscale Entropy (MSE) data. Using MSE data from different frequency bands and channels as features, the system explored a wide range of classifiers and observed their performance to see how they classified the features related to participants’ performance. The Artificial Bee Colony (ABC) method was used for feature selection to improve the process to make the system more efficient. The results showed that the system could correctly identify the differences between participants’ performance using MSE data and the ABC method with 95% confidence.     

A Novel Framework for Anomaly Detection for Satellite Momentum Wheel Based on Optimized SVM and Huffman-Multi-Scale Entropy

The health status of the momentum wheel is vital for a satellite. Recently, research on anomaly detection for satellites has become more and more extensive. Previous research mostly required simulation models for key components. However, the physical models are difficult to construct, and the simulation data does not match the telemetry data in engineering applications. To overcome the above problem, this paper proposes a new anomaly detection framework based on real telemetry data. First, the time-domain and frequency-domain features of the preprocessed telemetry signal are calculated, and the effective features are selected through evaluation. Second, a new Huffman-multi-scale entropy (HMSE) system is proposed, which can effectively improve the discrimination between different data types. Third, this paper adopts a multi-class SVM model based on the directed acyclic graph (DAG) principle and proposes an improved adaptive particle swarm optimization (APSO) method to train the SVM model. The proposed method is applied to anomaly detection for satellite momentum wheel voltage telemetry data. The recognition accuracy and detection rate of the method proposed in this paper can reach 99.60% and 99.87%. Compared with other methods, the proposed method can effectively improve the recognition accuracy and detection rate, and it can also effectively reduce the false alarm rate and the missed alarm rate.     

An Efficient DenseNet-Based Deep Learning Model for Malware Detection

Recently, there has been a huge rise in malware growth, which creates a significant security threat to organizations and individuals. Despite the incessant efforts of cybersecurity research to defend against malware threats, malware developers discover new ways to evade these defense techniques. Traditional static and dynamic analysis methods are ineffective in identifying new malware and pose high overhead in terms of memory and time. Typical machine learning approaches that train a classifier based on handcrafted features are also not sufficiently potent against these evasive techniques and require more efforts due to feature-engineering. Recent malware detectors indicate performance degradation due to class imbalance in malware datasets. To resolve these challenges, this work adopts a visualization-based method, where malware binaries are depicted as two-dimensional images and classified by a deep learning model. We propose an efficient malware detection system based on deep learning. The system uses a reweighted class-balanced loss function in the final classification layer of the DenseNet model to achieve significant performance improvements in classifying malware by handling imbalanced data issues. Comprehensive experiments performed on four benchmark malware datasets show that the proposed approach can detect new malware samples with higher accuracy (98.23% for the Malimg dataset, 98.46% for the BIG 2015 dataset, 98.21% for the MaleVis dataset, and 89.48% for the unseen Malicia dataset) and reduced false-positive rates when compared with conventional malware mitigation techniques while maintaining low computational time. The proposed malware detection solution is also reliable and effective against obfuscation attacks.     

Forest Fire Detection via Feature Entropy Guided Neural Network

Forest fire detection from videos or images is vital to forest firefighting. Most deep learning based approaches rely on converging image loss, which ignores the content from different fire scenes. In fact, complex content of images always has higher entropy. From this perspective, we propose a novel feature entropy guided neural network for forest fire detection, which is used to balance the content complexity of different training samples. Specifically, a larger weight is given to the feature of the sample with a high entropy source when calculating the classification loss. In addition, we also propose a color attention neural network, which mainly consists of several repeated multiple-blocks of color-attention modules (MCM). Each MCM module can extract the color feature information of fire adequately. The experimental results show that the performance of our proposed method outperforms the state-of-the-art methods.     

An Improved Residual Network for Pork Freshness Detection Using Near-Infrared Spectroscopy

Effective and rapid assessment of pork freshness is significant for monitoring pork quality. However, a traditional sensory evaluation method is subjective and physicochemical analysis is time-consuming. In this study, the near-infrared spectroscopy (NIRS) technique, a fast and non-destructive analysis method, is employed to determine pork freshness. Considering that commonly used statistical modeling methods require preprocessing data for satisfactory performance, this paper presents a one-dimensional squeeze-and-excitation residual network (1D-SE-ResNet) to construct the complex relationship between pork freshness and NIRS. The developed model enhances the one-dimensional residual network (1D-ResNet) with squeeze-and-excitation (SE) blocks. As a deep learning model, the proposed method is capable of extracting features from the input spectra automatically and can be used as an end-to-end model to simplify the modeling process. A comparison between the proposed method and five popular classification models indicates that the 1D-SE-ResNet achieves the best performance, with a classification accuracy of 93.72%. The research demonstrates that the NIRS analysis technique based on deep learning provides a promising tool for pork freshness detection and therefore is helpful for ensuring food safety.     

A Dynamic Anomaly Detection Approach Based on Permutation Entropy for Predicting Aging-Related Failures

Software aging is a phenomenon referring to the performance degradation of a long-running software system. This phenomenon is an accumulative process during execution, which will gradually lead the system from a normal state to a failure-prone state. It is a crucial challenge for system reliability to predict the Aging-Related Failures (ARFs) accurately. In this paper, permutation entropy (PE) is modified to Multidimensional Multi-scale Permutation Entropy (MMPE) as a novel aging indicator to detect performance anomalies, since MMPE is sensitive to dynamic state changes. An experiment is set on the distributed database system Voldemort, and MMPE is calculated based on the collected performance metrics during execution. Finally, based on MMPE, a failure prediction model using the machine learning method to reveal the anomalies is presented, which can predict failures with high accuracy.     

基于PLS子空间对齐的2,6-二甲酚纯度迁移学习建模

采用近红外光谱对物质浓度进行准确的在线检测对于生产优化具有重要意义。建立检测模型需要从近红外光谱中提取相关信息,代表性样本越多,提取的信息越有效,所建模型的精度越高。随着产品纯度的提高,样本的区分度下降,样本的变异系数小,多样性不足,并且存在测量噪声以及化验室人工检测样品浓度值时的测量误差,会导致物质浓度与光谱之间缺乏相关性,传统的建模方法无法建立可靠的近红外检测模型。为了解决这个问题,提出了一种基于PLS子空间对齐的迁移学习建模方法,应用于2,6-二甲酚精馏提纯过程中产品塔高纯度产品的在线检测。在制备化工单体2,6-二甲酚过程中,存在副反应和未反应完全的杂质,生产反应后的物料要顺序经过不同的精馏塔,最后在产品塔获得纯度高于99%的产品,产品塔的质量检测尤为重要。由于产品塔检测点近红外光谱数据缺乏多样性,检测模型的泛化能力较弱。该研究采用偏最小二乘为2,6-二甲酚精馏提纯过程中不同检测点的数据集创建子空间,然后通过最小化其他检测点数据子空间与产品塔检测点数据子空间的布雷格曼(Bregman)散度,将其他检测点数据的子空间对齐到产品塔数据子空间,减小其他检测点数据子空间与产品塔检测点数据...     

基于IFSR异常样本剔除的落叶松木材密度近红外优化模型的研究

木材密度可以反映木材的干缩性、抗压抗拉强度等多种物理性质,是重要的木材物理特性。采用近红外光谱技术能够实现木材密度的快速预测,可克服传统检测方法耗费人力、物力、时间的弊端,但建模结果往往受异常样本的影响。为准确识别并剔除样本集中的异常样本,提出一种孤立森林结合学生化残差方法(IFSR),在利用孤立森林集成特征的优点基础上考虑样本对模型的影响度,可同时检测异常样本与强影响样本。该研究对181个落叶松木材样本的近红外光谱及其在常温下的气干密度进行了测定。通过对比多种方法预处理和特征选择方法,确定采用标准正态变量变化(SNV)+去趋势处理(DT)+均值中心化(MC)+标准化(Auto)方法进行预处理,采用竞争性自适应重加权算法(CARS)进行特征波段选择,消除噪声及无关信息对算法的影响,简化数据集,提高算法剔除异常样本的准确性。为验证IFSR方法剔除异常样本的能力,将其与蒙特卡洛交互验证(MCCV)、马氏距离(MD)等其他六种异常检测方法对比分析,建立偏最小二乘(PLS)模型对其进行异常检测性能评价。同时在上述基础上采用粒子群寻优-支持向量机回归(PSO-SVR), BP神经网络(BPNN)...