Machine Learning-Based Alarms Classification and Correlation in an SDH/WDM Optical Network to Improve Network Maintenance

The evolution of telecommunications has allowed the development of broadband services based mainly on fiber optic backbone networks. The operation and maintenance of these optical networks is made possible by using supervision platforms that generate alarms that can be archived in the form of log files. But analyzing the alarms in the log files is a laborious and difficult task for the engineers who need a degree of expertise. Identifying failures and their root cause can be time consuming and impact the quality of service, network availability and service level agreements signed between the operator and its customers. Therefore, it is more than important to study the different possibilities of alarms classification and to use machine learning algorithms for alarms correlation in order to quickly determine the root causes of problems faster. We conducted a research case study on one of the operators in Cameroon who held an optical backbone based on SDH and WDM technologies with data collected from 2016-03-28 to “2022-09-01” with 7201 rows and 18. In this paper, we will classify alarms according to different criteria and use 02 unsupervised learning algorithms namely the K-Means algorithm and the DBSCAN to establish correlations between alarms in order to identify root causes of problems and reduce the time to troubleshoot. To achieve this objective, log files were exploited in order to obtain the root causes of the alarms, and then K-Means algorithm and the DBSCAN were used firstly to evaluate their performance and their capability to identify the root cause of alarms in optical network.

Systematic rationalization approach for multivariate correlated alarms based on interpretive structural modeling and Likert scale

Alarm flood is one of the main problems in the alarm systems of industrial process. Alarm root-cause analysis and alarm prioritization are good for alarm flood reduction. This paper proposes a systematic rationalization method for multivariate correlated alarms to realize the root cause analysis and alarm prioritization. An information fusion based interpretive structural model is constructed according to the data-driven partial correlation coefficient calculation and process knowledge modification. This hierarchical multi-layer model is helpful in abnormality propagation path identification and root-cause analysis. Revised Likert scale method is adopted to determine the alarm priority and reduce the blindness of alarm handling. As a case study, the Tennessee Eastman process is utilized to show the effectiveness and validity of proposed approach. Alarm system performance comparison shows that our rationalization methodology can reduce the alarm flood to some extent and improve the performance.

Dynamic alarm prediction for critical alarms using a probabilistic model

Alarm systems play important roles for the safe and efficient operation of modern industrial plants. Critical alarms are configured with a higher priority and are safety related among many other alarms. If critical alarms can be predicted in advance, the operator will have more time to prevent them from happening. In this paper,we present a dynamic alarm prediction algorithm, which is a probabilistic model that utilizes alarm data from distributed control system, to calculate the occurrence probability of critical alarms. It accounts for the local interdependences among the alarms using the n-gram model, which occur because of the nonlinear relationships between variables. Finally, the dynamic alarm prediction algorithm is applied to an industrial case study.

Prioritizing Alarms in Real-Time： Intelligent Alarms Advanced System

During the operation of complex process, such as oil production or refming, abnormal situations may occur, leading to an alarm flooding. Alarm flooding is the signalling of a large number of alarms in a few minutes, in such a way that it is impossible for the operator to attend to all alarms. On these occasions, it is usual that the operator leaves the alarm summary list and gets an analysis of the plant through the screens of the DCS （digital control system）, seeking to understand the situation. The alarm summary list ceases to be a useful tool. In such cases, the operator might have the aid of a filter that would present the highest priority alarms and other information associated with them, enabling him to gain a better knowledge of the situation. This paper describes the interface of a system aimed to help the operator to have a more comprehensive knowledge of the process （a better situational awareness） during process upsets that cause alarm flooding, recovering the utility of the alarm layer to the safety of industrial processes.

Sounding the alarm:Functionally referential signaling in Azure-winged Magpie

Functionally referential signals are a complex form of communication that conveys information about the external environment.Such signals have been found in a range of mammal and bird species and have helped us understand the complexities of animal communication.Corvids are well known for their extraordinary cognitive abilities,but relatively little attention has been paid to their vocal function.Here,we investigated the functionally referential signals of a cooperatively breeding corvid species,Azure-winged Magpie(Cyanopica cyanus).Through field observations,we suggest that Azure-winged Magpie uses referential alarm calls to distinguish two types of threats:’rasp’ calls for terrestrial threats and ’chatter’ calls for aerial threats.A playback experiment revealed that Azure-winged Magpies responded to the two call types with qualitatively different behaviors.They sought cover by flying into the bushes in response to the ’chatter’ calls,and flew to or stayed at higher positions in response to ’rasp’ calls,displaying a shorter response time to ’chatter’ calls.Significant differences in acoustic structure were found between the two types of calls.Given the extensive cognitive abilities of corvids and the fact that referential signals were once thought to be unique to primates,these findings are important for expanding our understanding of social communication and language evolution.

Design of AI-Enhanced and Hardware-Supported Multimodal E-Skin for Environmental Object Recognition and Wireless Toxic Gas Alarm

Post-earthquake rescue missions are full of challenges due to the unstable structure of ruins and successive aftershocks.Most of the current rescue robots lack the ability to interact with environments,leading to low rescue efficiency.The multimodal electronic skin(e-skin)proposed not only reproduces the pressure,temperature,and humidity sensing capabilities of natural skin but also develops sensing functions beyond it—perceiving object proximity and NO2 gas.Its multilayer stacked structure based on Ecoflex and organohydrogel endows the e-skin with mechanical properties similar to natural skin.Rescue robots integrated with multimodal e-skin and artificial intelligence(AI)algorithms show strong environmental perception capabilities and can accurately distinguish objects and identify human limbs through grasping,laying the foundation for automated post-earthquake rescue.Besides,the combination of e-skin and NO2 wireless alarm circuits allows robots to sense toxic gases in the environment in real time,thereby adopting appropriate measures to protect trapped people from the toxic environment.Multimodal e-skin powered by AI algorithms and hardware circuits exhibits powerful environmental perception and information processing capabilities,which,as an interface for interaction with the physical world,dramatically expands intelligent robots’application scenarios.

Adaptive detection of range-spread targets in homogeneous and partially homogeneous clutter plus subspace interference

Adaptive detection of range-spread targets is considered in the presence of subspace interference plus Gaussian clutter with unknown covariance matrix.The target signal and interference are supposed to lie in two linearly independent subspaces with deterministic but unknown coordinates.Relying on the two-step criteria,two adaptive detectors based on Gradient tests are proposed,in homogeneous and partially homogeneous clutter plus subspace interference,respectively.Both of the proposed detectors exhibit theoretically constant false alarm rate property against unknown clutter covariance matrix as well as the power level.Numerical results show that,the proposed detectors have better performance than their existing counterparts,especially for mismatches in the signal steering vectors.

A lightweight false alarm suppression method in heterogeneous change detection

Overlooking the issue of false alarm suppression in heterogeneous change detection leads to inferior detection per-formance.This paper proposes a method to handle false alarms in heterogeneous change detection.A lightweight network of two channels is bulit based on the combination of convolutional neural network(CNN)and graph convolutional network(GCN).CNNs learn feature difference maps of multitemporal images,and attention modules adaptively fuse CNN-based and graph-based features for different scales.GCNs with a new kernel filter adaptively distinguish between nodes with the same and those with different labels,generating change maps.Experimental evaluation on two datasets validates the efficacy of the pro-posed method in addressing false alarms.

Smoke Alarms for Informal Settlements: Monitoring and Challenges from a Large‑Scale Community Rollout in Cape Town, South Africa

This article presents the findings of a pilot project to test the large-scale rollout of smoke alarms in an informal community in Cape Town, South Africa. The work provides novel insight into the effectiveness and challenges associated with using smoke detectors in low-income communities. Technical details and detector considerations are also provided that will assist in enhancing future interventions.The project installed 1200 smoke detection devices in TRA informal settlement in the suburb of Wallacedene, in the City of Cape Town, and monitored their effectiveness for a period of 12 months. The monitoring showed that there were 11 real activations, where the presence of the devices likely saved lives and homes. The project also identified a series of challenges, especially in relation to nuisance alarms,where everyday household emissions, dust, and insect ingress caused false alarms, leading some participants to uninstall devices. The findings of the pilot study suggest that although smoke detectors could provide a valuable tool for reducing the frequency and impact of informal settlement fires in South Africa and elsewhere, they need to be adapted to meet the specific needs and conditions encountered in informal dwellings. Modifications, such as adjusting device sensitivity,preventing dust and insect ingress and tailoring devices to everyday conditions, will be essential to make smoke alarms more suitable and effective in the future. Smoke alarms could become an important component of low-income community fire safety if such challenges can be addressed.

Design of Signal Lamp Filament Monitoring Alarm Instrument

To improve the reliability of the light emitting diode(LED)signal lamp filament current monitoring alarm instrument for metro systems,a new type of hot standby online monitoring apparatus was developed which is based on synchronous transmission data(STD)bus technology.In this system,a double hot standby mode can be achieved by adopting bus arbitration.In addition,to detect the effective value of alternating current which is from 0 to 200 mA in the signal lamp lighting circuit,a precision rectifier signal conditioning circuit and an isolated acquisition circuit were designed.This new type of alarm instrument has high detection accuracy and could meet the functional requirements for metro signal systems after comparing it with some industry products that were applied on the spot.

With 11th Bride,King Alarms Health Workers

斯威士兰的国王,最近宣布他将娶一个17岁的女孩作为他的第11任妻 子。消息传出,全国哗然。个中原因,本文的末尾有明确交代。国王两年之前曾经宣布:…teenage girls should remain virgins(贞洁)to help stem(阻止)theAIDS crisis in Swaziland,where the adult HIV infection rate is approaching 40percent.

Modeling Target Detection and Performance Analysis of Electronic Countermeasures for Phased Radar

Interference is a key factor in radar return misdetection.Strong interference might make it difficult to detect the signal or targets.When interference occurs in the sidelobes of the antenna pattern,Sidelobe Cancellation(SLC)and Sidelobe Blanking are two unique solutions to solve this problem(SLB).Aside from this approach,the probability of false alert and likelihood of detection are the most essential parameters in radar.The chance of a false alarm for any radar system should be minimal,and as a result,the probability of detection should be high.There are several interference cancellation strategies in the literature that are used to sustain consistent false alarms regardless of the clutter environment.With the necessity for interference cancellation methods and the constant false alarm rate(CFAR),the Maisel SLC algorithm has been modified to create a new algorithm for recognizing targets in the presence of severe interference.The received radar returns and interference are simulated as non-stationary in this approach,and side-lobe interference is cancelled using an adaptive algorithm.By comparing the performance of adaptive algorithms,simulation results are shown.In a severe clutter situation,the simulation results demonstrate a considerable increase in target recognition and signal to noise ratio when compared to the previous technique.

Pattern Matching of Industrial Alarm Floods Using Word Embedding and Dynamic Time Warping

Dear Editor,This letter proposes a new pattern matching method based on word embedding and dynamic time warping(DTW)to identify groups of similar alarm floods.First,alarm messages are transformed into numeric values that represent alarms and also reflect the relationships between alarm occurrences.Then,similarities between numerically encoded alarm flood sequences are calculated by DTW and groups of similar floods are identified via clustering.The effectiveness of the proposed method is demonstrated by a case study with alarm&event data obtained from a public industrial simulation model.

Antipredatory call behavior of lapwing species in an Afrotropical environment

Predation is an important source of natural selection on prey species and has resulted in adaptations such as antipredator vocal signals,which can alert others to the presence of predators and solicit cooperative attack.Although vocal alarm signals of birds have been well studied,they are poorly known in tropical African species.To address this lack of information,the antipredatory signals and responses of two lapwings(Wattled Lapwing Vanellus senegallus and Spur-winged Lapwing Vanellus spinosus)to potential predators were investigated using data collected from focal observation,distance measurements,focal recordings,and playback experiment.The lapwing calls elicited to predators were classified as alarm or mobbing calls based on whether the calls elicited alert behavior or attack from other lapwings.Discriminant linear analysis(DLA)was used to compare the time and frequency parameters of the call types measured in Raven PRO.Also,lapwings’responses to intruders,alert and start distance,time of day,and latency,as well as the effects of flock size and distance to cover were examined.About 48%of all calls was correctly classified by DLA.The best predictors of call type for the lapwings were maximum frequency and high frequency.Both alarm and mobbing calls were elicited by African Wattled Lapwings to dogs and humans.Mobbing calls were elicited to intruders by the Spur-winged Lapwings.Alert distance was positively associated with start distance,and differed between morning and evening in both lapwings.With scarce information from tropical Africa,this study put in perspective vocal and antipredator behavior of lapwing species in Africa.

Multi-Attack Intrusion Detection System for Software-Defined Internet of Things Network

Currently,the Internet of Things(IoT)is revolutionizing communi-cation technology by facilitating the sharing of information between different physical devices connected to a network.To improve control,customization,flexibility,and reduce network maintenance costs,a new Software-Defined Network(SDN)technology must be used in this infrastructure.Despite the various advantages of combining SDN and IoT,this environment is more vulnerable to various attacks due to the centralization of control.Most methods to ensure IoT security are designed to detect Distributed Denial-of-Service(DDoS)attacks,but they often lack mechanisms to mitigate their severity.This paper proposes a Multi-Attack Intrusion Detection System(MAIDS)for Software-Defined IoT Networks(SDN-IoT).The proposed scheme uses two machine-learning algorithms to improve detection efficiency and provide a mechanism to prevent false alarms.First,a comparative analysis of the most commonly used machine-learning algorithms to secure the SDN was performed on two datasets:the Network Security Laboratory Knowledge Discovery in Databases(NSL-KDD)and the Canadian Institute for Cyberse-curity Intrusion Detection Systems(CICIDS2017),to select the most suitable algorithms for the proposed scheme and for securing SDN-IoT systems.The algorithms evaluated include Extreme Gradient Boosting(XGBoost),K-Nearest Neighbor(KNN),Random Forest(RF),Support Vector Machine(SVM),and Logistic Regression(LR).Second,an algorithm for selecting the best dataset for machine learning in Intrusion Detection Systems(IDS)was developed to enable effective comparison between the datasets used in the development of the security scheme.The results showed that XGBoost and RF are the best algorithms to ensure the security of SDN-IoT and to be applied in the proposed security system,with average accuracies of 99.88%and 99.89%,respectively.Furthermore,the proposed security scheme reduced the false alarm rate by 33.23%,which is a significant improvement over prevalent schemes.Finally,tests of the algorithm for dataset selection showed that the rates of false positives and false negatives were reduced when the XGBoost and RF algorithms were trained on the CICIDS2017 dataset,making it the best for IDS compared to the NSL-KDD dataset.

Glass-compatible and self-powered temperature alarm system by temperature-responsive organic manganese halides via backward energy transfer process

A pioneering glass-compatible transparent temperature alarm system self-powered by luminescent solar concentrators(LSCs) is reported.Single green-emitted organic manganese halides(OMHs) of PEA_(2)MnBr_(2)I_(2),which has a unique temperature-dependent backward energy transfer process from selftrapped state to^(4)T_(1)energy level of Mn,is used for triggering the temperature alarm.The LSC with redemitted CsPbI_(3)perovskite-polymer composite films on the glass substrate is used for power supply.The spectrally separated nature between the green-emitted OMHs for temperature alarm and red-emitted CsPbI3in LSC for power supply allows for probing the signal light of temperature-responsive OMHs without the interference of LSCs,making it possible to calibrate the temperature visually just by a self-powered brightness detection circuit with LED indicators.Taking advantage of LSC without hot spot effects plaguing the solar cells,as-prepared temperature alarm system can operate well on both sunny and cloudy day.

SCADA Data-Based Support Vector Machine for False Alarm Identification for Wind Turbine Management

Maintenance operations have a critical influence on power gen-eration by wind turbines(WT).Advanced algorithms must analyze large volume of data from condition monitoring systems(CMS)to determine the actual working conditions and avoid false alarms.This paper proposes different support vector machine(SVM)algorithms for the prediction and detection of false alarms.K-Fold cross-validation(CV)is applied to evaluate the classification reliability of these algorithms.Supervisory Control and Data Acquisition(SCADA)data from an operating WT are applied to test the proposed approach.The results from the quadratic SVM showed an accuracy rate of 98.6%.Misclassifications from the confusion matrix,alarm log and maintenance records are analyzed to obtain quantitative information and determine if it is a false alarm.The classifier reduces the number of false alarms called misclassifications by 25%.These results demonstrate that the proposed approach presents high reliability and accuracy in false alarm identification.

A New Two-Stage Tunable Space-Time Adaptive Detector

In order to improve the rejection capability of mismatched interferer signals,a new two-stage detector is proposed under homogeneous scenarios with unknown covariance matrix,which is obtained by cascading the adaptive matched filter(AMF)detector and the enhanced RAO(EnRAO)detector.The new detector has constant false alarm performance,and the closed-form expression of probability of false alarm and probability of detection is derived.The performance of the new detector is assessed,and analyzed in comparison with other detectors.The results show that,the proposed detector can provide enhanced rejection capability in the case of mismatch,but the performance of the detector is slightly lost under the condition of matching.

Doppler Radar Fault Judgment System and Remote Monitoring Platform

The Doppler weather radar fault judging system and remote monitoring platform were introduced.Through the real-time scanning of radar alarm information coding,the platform can realize dynamic monitoring and real-time alarm of Doppler radar equipment components,so as to improve the reliability of equipment operation,and truly realize"unattended"remote monitoring.

Enhancing Feature Discretization in Alarm and Fire Detection Systems Using Probabilistic Inference Models

Sensors for fire alarms require a high level of predictive variables to ensure accurate detection, injury prevention, and loss prevention. Bayesian networks can aid in enhancing early fire detection capabilities and reducing the frequency of erroneous fire alerts, thereby enhancing the effectiveness of numerous safety monitoring systems. This research explores the development of optimized probabilistic graphic models for the discretization thresholds of alarm system predictor variables. The study presents a statistical model framework that increases the efficacy of fire detection by predicting the discretization thresholds of alarm system predictor variable fluctuations used to detect the onset of fire. The work applies the Bayesian networks and probabilistic visual models to reveal the specific characteristics required to cope with fire detection strategies and patterns. The adopted methodology utilizes a combination of prior knowledge and statistical data to draw conclusions from observations. Utilizing domain knowledge to compute conditional dependencies between network variables enabled predictions to be made through the application of specialized analytical and simulation techniques.