Anomalies In Real-time Research Articles

Application of LSTM Networks for Continuous Patient Monitoring and Anomaly Detection in Wearable Health Devices

Objectives: This paper looks into the application of LSTM networks in improving continuous patient monitoring and anomaly detection on wearable health devices by using accurate analysis of sequential physiological data. Methods: This paper presents a new use of LSTM networks, which are very powerful in the analysis of time series data, making them quite accurate in their predictions and thus adding functionality to wearable health devices. Our approach is to train an LSTM model on a huge dataset such as PhysioNet, which includes over 60,000 recordings of ECG signals from more than 50 different databases, encompassing a wide variety of physiological conditions and signal types, so the model learns across a wide range of health conditions and demographics. Findings: The proposed LSTM-based model reduces false positives by 30% and false negatives by 40%, hence improving anomaly detection accuracy by up to 30% over prior methods such as SVM, Random Forest, KNN, DBSCAN, TDL, and DQN. Novelty: This work uniquely enhances the existing literature by applying LSTM networks specifically to wearable health devices, optimizing the detection of health anomalies in real time with higher accuracy compared to traditional methods. It also introduces a novel approach to handling complex sequential physiological data, contributing to more reliable and timely medical interventions. Keywords: LSTM networks, Wearable Health Devices, Patient Monitoring, Anomaly Detection, Time-series data

Evaluating Multi-target Regression Framework for Dynamic Condition Prediction in Wellbore

In recent years, the focus has shifted towards leveraging physics-based modelling and data-driven analysis to predict drilling incidents and anomalies in real time, with the goal of reducing non-productive periods. However, much of this attention has directed at specific drilling operations like drilling and tripping, leaving other vital processes, such as wellbore conditioning, comparatively overlooked. The primary objective of this study is to employ data-driven techniques for predicting the dynamic state of the wellbore by utilising sensor data, operating parameters, and surface measurements. Accurate predictions are pivotal for automating these processes, promising significant savings in both redundant time and associated costs, ultimately elevating operational efficiency.In this research, the surface drilling parameters such as flowrate, rotation speed, block position, and drill string length are incorporated with the surface measurements such as hookload, pressure, and torque during wellbore conditioning operation to predict further surface sensor measurements. Different parameter settings are evaluated to find the best approach. Six supervised learning algorithms are used to select the best prediction method. The findings reveal that considering all surface parameters and measurements yields the most accurate predictions. Among various single and multi-target regression methods, including deep learning approaches, the Gaussian process and random forest models exhibit the lowest prediction errors.By reliably predicting and understanding wellbore behaviour, this research paves the way for more efficient and autonomous drilling operations in the future, bridging a critical gap in the industry's automation capabilities.

Deep Learning-Based Prognostics and Health Management Model for Pilot-Operated Cryogenic Safety Valves.

This paper highlights the significance of safety and reliability in modern industries, particularly in sectors like petroleum and LNG, where safety valves play a critical role in ensuring system safety under extreme conditions. To enhance the reliability of these valves, this study aims to develop a deep learning-based prognostics and health management (PHM) model. Past empirical methods have limitations, driving the need for data-driven prediction models. The proposed model monitors safety valve performance, detects anomalies in real time, and prevents accidents caused by system failures. The research focuses on collecting sensor data, analyzing trends for lifespan prediction and normal operation, and integrating data for anomaly detection. This study compares related research and existing models, presents detailed results, and discusses future research directions. Ultimately, this research contributes to the safe operation and anomaly detection of pilot-operated cryogenic safety valves in industrial settings.

Utilizing machine learning techniques for network traffic anomaly detection

The landscape of network traffic anomaly detection has evolved considerably in recent times, driven largely by the advent of pioneering algorithms. This article undertakes an exhaustive comparative exploration of some of the most contemporary algorithms, namely Prophet, Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN), Isolated Forest (IF), and OmniAnomaly. Delving deep into their distinctive features, functionalities, and practical applications, the paper sheds light on the factors that render these algorithms superior to their predecessors. The discourse commences with a prologue underscoring the escalating importance of network traffic anomaly detection, especially in the face of the burgeoning cyber threats of the modern era. This sets the stage for a presentation on the focal algorithms - Prophet, RNN, CNN, IF, and OmniAnomaly. Each algorithm is then dissected to provide readers with a nuanced understanding of its underlying mechanics and methodologies. Furthermore, the discourse amplifies the breakthroughs and innovations underpinning each algorithm, highlighting attributes such as heightened accuracy, lucid interpretability, proficiency in deciphering intricate patterns, and the agility to detect anomalies in real time. Factors like computational agility, resilience, structural intricacy, and versatility across varied operational terrains are assessed in a meticulous comparative framework. Drawing from empirical evidence available in extant literature, the article underscores the stellar performance of these algorithms, benchmarked using quantitative metrics like precision.

Distributed and explainable GHSOM for anomaly detection in sensor networks

The identification of anomalous activities is a challenging and crucially important task in sensor networks. This task is becoming increasingly complex with the increasing volume of data generated in real-world domains, and greatly benefits from the use of predictive models to identify anomalies in real time. A key use case for this task is the identification of misbehavior that may be caused by involuntary faults or deliberate actions. However, currently adopted anomaly detection methods are often affected by limitations such as the inability to analyze large-scale data, a reduced effectiveness when data presents multiple densities, a strong dependence on user-defined threshold configurations, and a lack of explainability in the extracted predictions. In this paper, we propose a distributed deep learning method that extends growing hierarchical self-organizing maps, originally designed for clustering tasks, to address anomaly detection tasks. The SOM-based modeling capabilities of the method enable the analysis of data with multiple densities, by exploiting multiple SOMs organized as a hierarchy. Our map-reduce implementation under Apache Spark allows the method to process and analyze large-scale sensor network data. An automatic threshold-tuning strategy reduces user efforts and increases the robustness of the method with respect to noisy instances. Moreover, an explainability component resorting to instance-based feature ranking emphasizes the most salient features influencing the decisions of the anomaly detection model, supporting users in their understanding of raised alerts. Experiments are conducted on five real-world sensor network datasets, including wind and photovoltaic energy production, vehicular traffic, and pedestrian flows. Our results show that the proposed method outperforms state-of-the-art anomaly detection competitors. Furthermore, a scalability analysis reveals that the method is able to scale linearly as the data volume presented increases, leveraging multiple worker nodes in a distributed computing setting. Qualitative analyses on the level of anomalous pollen in the air further emphasize the effectiveness of our proposed method, and its potential in determining the level of danger in raised alerts.

Safeguarding Critical Infrastructures: Machine Learning in Cybersecurity

It has become essential to protect vital infrastructures from cyber threats in an age where technology permeates every aspect of our lives. This article examines how machine learning and cybersecurity interact, providing a thorough overview of how this dynamic synergy might strengthen the defence of critical systems and services. The hazards to public safety and national security from cyberattacks on vital infrastructures including electricity grids, transportation networks, and healthcare systems are significant. Traditional security methods have failed to keep up with the increasingly sophisticated cyber threats. Machine learning offers a game-changing answer because of its ability to analyse big datasets and spot anomalies in real time. The goal of this study is to strengthen the defences of key infrastructures by applying machine learning algorithms, such as CNN, LSTM, and deep reinforcement learning for anomaly algorithm. These algorithms can anticipate weaknesses and reduce possible breaches by using historical data and continuously adapting to new threats. The research also looks at issues with data privacy, algorithm transparency, and adversarial threats that arise when applying machine learning to cybersecurity. For machine learning technologies to be deployed successfully, these obstacles must be removed. Protecting vital infrastructures is essential as we approach a day where connectivity is pervasive. This study provides a road map for utilising machine learning to safeguard the foundation of our contemporary society and make sure that our vital infrastructures are robust in the face of changing cyberthreats. The secret to a safer and more secure future is the marriage of cutting-edge technology with cybersecurity knowledge.

Monitoring of Road Irregularities Using Data Analytics

Abstract: This work presents a smartphone-based system that uses orientation and acceleration data to monitor and classify road anomalies in real time. Three severity levels—mild, moderate, and severe—are assigned to irregularities by the system, which also handles their identification, classification, and geotagging. Robust approaches are employed to acknowledge and mitigate challenges such as threshold determination, vehicle-specific vibrations, and smartphone orientation normalization. To ensure a thorough dataset, data collecting entails systematic trials for different types of irregularities. Kalman filtering for noise reduction and a consistent 200 Hz sample rate are used in further preprocessing. A variety of indicators from the Y-axis data are included in feature extraction, which produces a complex dataset for model training. The decision tree approach is used to identify road segments based on extracted data because of its interpretability and transparency

Anomaly detection analysis based on correlation of features in graph neural network

Various studies have been conducted to detect network anomalies. However, because anomaly signals are determined by the pattern characteristics using the dataset, the real-time detection problem continues. Even if there is a signal with an attack sign among the constantly transmitted and received signals, the attack cannot be blocked in advance. Moreover, it appears in many places in a distributed denial-of-service (DDoS) attack, so the real-time defense must be the best option. Therefore, it is necessary first to discover the characteristics and elements regarded as abnormal signals to discover anomalies in real time. Finally, by analyzing the correlation between network data and features, extracting the elements of the anomaly, and analyzing the behavior of the extracted elements in detail, we aim to increase the accuracy of the anomaly. In this study, we used Coburg intrusion detection and KDDCup datasets and analyzed the correlation of elements in the dataset using a graph neural network. The calculated accuracy values of the anomaly detection were 94.5% and 98.85%.

A systematic investigation of radiation collapse for disruption avoidance and prevention on JET tokamak

To produce fusion reactions efficiently, thermonuclear plasmas have to reach extremely high temperatures, which is incompatible with their coming into contact with material surfaces. Confinement of plasmas using magnetic fields has progressed significantly in the last years, particularly in the tokamak configuration. Unfortunately, all tokamak devices, and particularly metallic ones, are plagued by catastrophic events called disruptions. Many disruptions are preceded by anomalies in the radiation patterns, particularly in ITER-relevant scenarios. These specific forms of radiation emission either directly cause or reveal the approaching collapse of the configuration. Detecting the localization of these radiation anomalies in real time requires an innovative and specific elaboration of bolometric measurements, confirmed by visible cameras and the inversion of sophisticated tomographic algorithms. The information derived from these measurements can be interpreted in terms of local power balances, which suggest a new quantity, the radiated power divided by the plasma internal energy, to determine the criticality of the plasma state. Combined with robust indicators of the temperature profile shape, the identified anomalous radiation patterns allow determination of the sequence of macroscopic events leading to disruptions. A systematic analysis of JET campaigns at high power in deuterium, full tritium, and DT, for a total of almost 2000 discharges, proves the effectiveness of the approach. The warning times are such that, depending on the radiation anomaly and the available actuators, the control system of future devices is expected to provide enough notice to enable deployment of effective prevention and avoidance strategies.

Research on Forecasting of the Compressor Geometric Variable System Based on the MAE Model

The compressor geometric variable system is vital for aeroengines, as it affects their performance and design. To monitor the compressor geometric variable system states and detect anomalies in real time, a t -step forecasting method based on the MAE (masked autoencoders) model was proposed in this article. Unlike previous studies that used simulated or lab-generated data, we use actual flight data recorded by the aircraft data acquisition system to make our results more realistic. Through our experimental efforts, the feasibility of forecasting the compressor geometric variable system based on the MAE model is verified. That is not only the first application of transformer models with a masked pretraining mechanism in time series forecasts but also taking the lead in exploring the possibility of this key system forecast. We also test the generalizability of our method across different types of aeroengines. Finally, to make our theories more reasonable and convincing, experiments on different aeroengine states, including the transition state and the steady state, are carried out.

A novel dynamic distance coding identification method for oil–gas gathering and transportation process

Deep learning (DL) has become a mainstream method for fault identification in petrochemical processes. However, the high noise and nonlinear coupling of complex data samples have led to different degrees of low accuracy and robustness problems in the method. Meanwhile, the fault cause is difficult to capture due to the complex chemical process operation mechanism. To address this challenge, a novel dynamic distance coding method incorporating DL is proposed to identify anomalies in real time. First, the collected normal process data are smoothed by the Savitzky–Golay filter to build a normal sample set. Then, dynamic coding based on the distance metric is introduced to compute the distribution of normal and real-time samples for extracting the spatial domain features. By a sliding window, dynamic coded maps are generated and analyzed for fault causes. Finally, the time-domain information is extracted by long short-term memory (LSTM) to learn the deep features of the encoded graph for fault identification. The proposed method was applied to an oil–gas gathering and transportation process, which proves its feasibility and effectiveness. Compared with the conventional LSTM, the F1 score of the method is improved by 0.193, reaching 0.986. The obtained visualization information enables explaining the causes and supplements the fault database, providing a valuable reference for workers’ feedback operations.

An ensemble-based framework for user behaviour anomaly detection and classification for cybersecurity

Nowadays, the speed of the user and application logs is so quick that it is almost impossible to analyse them in real time without using high-performance systems and platforms. In cybersecurity, human behaviour is responsible directly or indirectly for the most common attacks (i.e. ransomware and phishing). To monitor user behaviour, it is necessary to process fast user logs coming from different and heterogeneous sources, having part of the data or some entire sources missing. A framework based on the elastic stack (ELK) to process and store log data in real time from different users and applications is proposed for this aim. This system generates an ensemble of models to classify user behaviour and detect anomalies in real time, exploiting the advantages of the ELK-based software architecture and of the Kubernetes platform. In addition, a distributed evolutionary algorithm is used to classify the users by exploiting their digital footprints derived from many data sources. Experiments conducted on two real-life data sets verify the approach’s goodness in detecting anomalies in user behaviour, coping with missing data and lowering the number of false alarms.

Hierarchical Domain-Based Multicontroller Deployment Strategy in SDN-Enabled Space–Air–Ground Integrated Network

The space–air–ground integrated network (SAGIN) is considered to be a significant framework for realizing the vision of “6G intelligent connection of all things.” A typical SAGIN consists of three parts: a space-based network composed of various orbiting satellites, an air-based network composed of aircraft, and a traditional ground-based network. Considering the cost of satellite launch, the network needs to be flexible and controllable. In order to ensure that the ground can handle satellite anomalies in real time by program, it is necessary to introduce in-orbit programmable networks, such as the software-defined network (SDN). In the network management architecture, if the controller plane in the SDN adopts the flat management scheme, the expansion of the control plane is limited due to the low efficiency of data synchronization among controllers. Compared with controller deployments on terrestrial networks, multicontroller deployments in the SAGIN face the following problems: the dynamic change of the satellite network topology, the large-scale network nodes, the increase or decrease in the number of aerial vehicles, and the unbalanced distribution of ground users. Therefore, it is of great significance to study how to optimize the deployment of multiple controllers in the SDN-enabled SAGIN. This article introduces an SDN into the SAGIN and designs a hierarchical domain-based SDN-enabled SAGIN architecture. A multicontroller deployment strategy for the hierarchical domain-based SDN-enabled SAGIN is proposed. First, we divide the SDN control plane into two layers, i.e., the primary controller layer is deployed on the ground network and the secondary on the space-based network. The SDN data plane is composed of space-based, air-based, and ground-based networks. Second, considering the average network delay and the controller load, a multiobjective optimization model is constructed. To determine the number of controllers and the relative positions of switch nodes and controllers, the clustering algorithm based on <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> -means is adopted to initially divide the data plane. Finally, to improve the global search ability of the algorithm, a multiobjective optimization algorithm based on a genetic algorithm is adopted. The simulation results show that the proposed strategy is effective in reducing the average network delay and improving the controller load balance. Compared to other algorithms, the average network delay is reduced by 13.3% and the controller load is improved by 10.33%.

Compressed Smooth Sparse Decomposition

Image-based anomaly detection systems are of vital importance in various manufacturing applications. The resolution and acquisition rate of such systems are increasing significant in recent years under the fast development of image sensing technology. This enables the detection of tiny anomalies in real time. However, such a high resolution and a high acquisition rate of image data not only slow down the speed of image processing algorithms but also, increase data storage and transmission cost. To tackle this problem, we propose a fast and data-efficient method with theoretical performance guarantee that is suitable for sparse anomaly detection in images with a smooth background (smooth plus sparse signal). The proposed method, named compressed smooth sparse decomposition (CSSD), is a one-step method that unifies the compressive image acquisition- and decomposition-based image processing techniques. To further enhance its performance in a high-dimensional scenario, a Kronecker compressed smooth sparse decomposition (KronCSSD) method is proposed. Compared with traditional smooth and sparse decomposition algorithms, significant transmission cost reduction and computational speed boost can be achieved with negligible performance loss. Simulation examples and several case studies in various applications illustrate the effectiveness of the proposed framework. History: Kwok-Leung Tsui served as the senior editor for this article. Funding: This work is partially support by the National Science Foundation Division of Engineering Education and Centers [Grant 2052714]. Data Ethics &amp; Reproducibility Note: The code capsule is available on Code Ocean at https://doi.org/10.24433/CO.6352310.v2 and in the e-Companion to this article (available at https://doi.org/10.1287/ijds.2022.0023 ).

Fog computing application of cyber-physical models of IoT devices with symbolic approximation algorithms

Smart manufacturing systems based on cloud computing deal with large amounts of data for various IoT devices, resulting in several challenges, including high latency and high bandwidth usage. Since fog computing physically close to IoT devices can alleviate these issues, much attention has recently been focused on this area. Fans are nearly ubiquitous in manufacturing sites for cooling and ventilation purposes. Thereby, we built a fan system with an accelerometer installed and monitored the operating state of the fan. We analyzed time-series data transmitted from the accelerometer. We applied machine learning under streaming data analytics at the fog computing level to create a fan’s cyber-physical model (CPM). This work employed the symbolic approximation algorithm to approximate the time series data as symbols of arbitrary length. We compared the performance of CPMs made with five time-series classification (TSC) algorithms to monitor the state of the fan for anomalies in real time. The CPM made with the BOSS VS algorithm, a symbol approximation algorithm, accurately determined the current state of the fan within a fog computing environment, achieving approximately 98% accuracy at a 95% confidence level. Furthermore, we conducted a posthoc analysis, running statistical rigor tests on experimental data and simulation results. The workflow proposed in this work would be expected to be utilized for various IoT devices in smart manufacturing systems.

Online monitoring of profiles via function‐on‐scalar model with an application to industrial busbar

AbstractIn Statistical Process Control, profile monitoring is used for monitoring whether the process is in‐control or not by checking the relationship stability between the process response and covariates. In the industrial process recently, the functional relationship between the process variables is more and more complex, and the profile data are often time‐dependent and subject to within‐profile autocorrelation. We need to use appropriate models to characterize these complex relationships, and design new profile monitoring schemes to ensure satisfactory process monitoring performance. This paper studies a practical nonparametric profile monitoring problem, in which the functional relationship is in the form of function‐on‐scalar and within‐profile data are autocorrelated. A new online profile monitoring scheme is proposed to monitor process anomalies in real time. In Phase Ⅰ, based on the in‐control historical data, the model for the process is established estimated. Then, using the monitoring statistics based on penalty spline smoothing, the function‐on‐scalar monitoring parameters control scheme with a moving window is presented, and is applied to the anomaly monitoring of online sequential profile data. A large number of numerical simulation results show that in the presence of the function‐on‐scalar relationship, the proposed scheme has a superior performance in various cases. Finally, an application example of industrial busbar running process monitoring is given to illustrate the effectiveness of the scheme.

A Neural Algorithm for the Detection and Correction of Anomalies: Application to the Landing of an Airplane.

The location of the plane is key during the landing operation. A set of sensors provides data to get the best estimation of plane localization. However, data can contain anomalies. To guarantee correct behavior of the sensors, anomalies must be detected. Then, either the faulty sensor is isolated or the detected anomaly is filtered. This article presents a new neural algorithm for the detection and correction of anomalies named NADCA. This algorithm uses a compact deep learning prediction model and has been evaluated using real and simulated anomalies in real landing signals. NADCA detects and corrects both fast-changing and slow-moving anomalies; it is robust regardless of the degree of oscillation of the signals and sensors with abnormal behavior do not need to be isolated. NADCA can detect and correct anomalies in real time regardless of sensor accuracy. Likewise, NADCA can deal with simultaneous anomalies in different sensors and avoid possible problems of coupling between signals. From a technical point of view, NADCA uses a new prediction method and a new approach to obtain a smoothed signal in real time. NADCA has been developed to detect and correct anomalies during the landing of an airplane, hence improving the information presented to the pilot. Nevertheless, NADCA is a general-purpose algorithm that could be useful in other contexts. NADCA evaluation has given an average F-score value of 0.97 for anomaly detection and an average root mean square error (RMSE) value of 2.10 for anomaly correction.

Deep Learning Based Intrusion Detection in Cloud Services for Resilience Management

In the global scenario one of the important goals for sustainable development in industrial field is innovate new technology, and invest in building infrastructure. All the developed and developing countries focus on building resilient infrastructure and promote sustainable developments by fostering innovation. At this juncture the cloud computing has become an important information and communication technologies model influencing sustainable development of the industries in the developing countries. As part of the innovations happening in the industrial sector, a new concept termed as ‘smart manufacturing’ has emerged, which employs the benefits of emerging technologies like internet of things and cloud computing. Cloud services deliver an on-demand access to computing, storage, and infrastructural platforms for the industrial users through Internet. In the recent era of information technology the number of business and individual users of cloud services have been increased and larger volumes of data is being processed and stored in it. As a consequence, the data breaches in the cloud services are also increasing day by day. Due to various security vulnerabilities in the cloud architecture; as a result the cloud environment has become non-resilient. To restore the normal behavior of the cloud, detect the deviations, and achieve higher resilience, anomaly detection becomes essential. The deep learning architectures-based anomaly detection mechanisms uses various monitoring metrics characterize the normal behavior of cloud services and identify the abnormal events. This paper focuses on designing an intelligent deep learning based approach for detecting cloud anomalies in real time to make it more resilient. The deep learning models are trained using features extracted from the system level and network level performance metrics observed in the Transfer Control Protocol (TCP) traces of the simulation. The experimental results of the proposed approach demonstrate a superior performance in terms of higher detection rate and lower false alarm rate when compared to the Support Vector Machine (SVM).

An unsupervised anomaly detection framework for detecting anomalies in real time through network system’s log files analysis

Nowadays, in almost every computer system, log files are used to keep records of occurring events. Those log files are then used for analyzing and debugging system failures. Due to this important utility, researchers have worked on finding fast and efficient ways to detect anomalies in a computer system by analyzing its log records. Research in log-based anomaly detection can be divided into two main categories: batch log-based anomaly detection and streaming log- based anomaly detection. Batch log-based anomaly detection is computationally heavy and does not allow us to instantaneously detect anomalies. On the other hand, streaming anomaly detection allows for immediate alert. However, current streaming approaches are mainly supervised. In this work, we propose a fully unsupervised framework which can detect anomalies in real time. We test our framework on hdfs log files and successfully detect anomalies with an F-1 score of 83%.

A Spatial-Temporal Feature Extraction and Unsupervised Recognition of Video Anomalies in Real Time

Anomaly detection is an area of video analysis has a great importance in automated surveillance. Although it has been extensively studied, there has been little work started using CNN networks. Hence, in this thesis we presented a novel approach for learning motion features and modeling normal Spatio-temporal dynamics for anomaly detection. In our technique, we capture variations in scale of the patterns of motion in an image object by using optical flow dense estimation technique and train our auto encoder model using convolution long short term memories (ConvLSTM2D) as we are processing video frames and we predict the anomaly in real time using Euclidean distance between the generated and the ground truth frame and we achieved a real time accuracy of nearly 98% for the youtube videos which are not used for either testing or training. Error between the network’s output and the target output is used to classify a video volume as normal or abnormal. In addition to the use of reconstruction error, we also use prediction error for anomaly detection. The prediction models show comparable performance with state of the art methods. In comparison with the proposed method, performance is improved in one dataset. Moreover, running time is significantly faster.