True Alarms Research Articles

A production-inventory model under quality-maintenance policy with rework process in the presence of random failures and multiple assignable causes

ABSTRACT This research presents simultaneous design of production planning, maintenance strategy and control chart in which two issues are considered: (1) multiple assignable cause and (2) equipment failure. The first one means that various factors may shift the process to an out-of-control state; while the second one means that the equipment is not always available and may be suddenly failed. Also, to reduce the production costs, a rework process is performed on the nonconforming items right after the regular cycle. Furthermore, three types of maintenance activities are applied based on system conditions. The corrective maintenance is conducted when the equipment failure occurs. The preventive maintenance is accomplished when the process continues until the end of the cycle, and the predictive maintenance is performed whereas the chart issues a true alarm. To check the effectiveness of the model, three comparative studies are examined. The first one compares the suggested model with a similar model without the rework process; the second one demonstrates the importance of employing the statistical process monitoring; and the last one compares the model with a similar model without considering the equipment failure. The results show the superiority of the integrated model compared to the others in the cost-saving.

PER4Mance Prototyping environment for research on human-machine interactions for alarm floods management: the case study of a chemical plant process control

Alarm floods are dangerous because the quantity of alarms triggered is too numerous for operators to reliably implement the right corrective action. Process operators of complex systems, such as chemical plants or nuclear power production, are faced with alarm management systems that can be better built in consideration of human capabilities and limitations. Developing human-machine interfaces (HMIs) that better support operators is critical for ensuring the safe and reliable operation of critical systems and processes. The research team has developed an accessible and adaptable prototyping environment dedicated for research on alarm management and human-machine interactions in the process industry. The method used was to build on the Tennessee Eastman Process (TEP) simulator and incorporate Human-Machine design guidelines. The results are an open-sourced prototyping environment that incorporates data from a real chemical plant and integrates true alarm data and thresholds. At the end of this article, we share the Github link to the entire MATLAB, Simulink and App Designer files of PER4Mance: a prototyping environment for research on human-machine interactions for alarm flood management.

The Impact of False Alarms on Mental Workload, Stress and Performance: Implications for Medical Settings

The excessive number of auditory and false alarms (FAs) in medical settings (e.g. ICUs) negatively impact alarm response and performance on ongoing tasks. We examined the impact of two FA rates (low-40% and high-80% in a counterbalanced order repeated measures design) on 36 participants’ alarm responses with a concurrent working-memory (N-back) task. Participants made significantly more responses to FAs in the high FA condition relative to the low FA condition. An FA rate and order interaction revealed that participants who started in the low FA condition responded to fewer FAs in both the high and low FA conditions. Participants who started in the high FA condition responded to more than twice the number of FAs in the high FA condition compared to the low FA condition. Similarly, response time to correct detections (Hits) in the alarm and N-back tasks also revealed interaction effects between order and FA conditions. Participants who received the low FA condition first responded faster to true alarms in the high FA condition compared to those who received the high FA condition first. No significant main effects or interactions were observed for the number of Hits on the alarm task, response times to FAs in either task, nor for subjective ratings of mental workload or stress. Significant main and interaction effects observed on the N-back task were likely attributable to practice effects. These results underscore the need to reduce the number of FAs in medical settings and have implications for designing training paradigms to improve provider performance.

Deep Reinforcement Learning Ensemble for Detecting Anomaly in Telemetry Water Level Data

Water levels in rivers are measured by various devices installed mostly in remote locations along the rivers, and the collected data are then transmitted via telemetry systems to a data centre for further analysis and utilisation, including producing early warnings for risk situations. So, the data quality is essential. However, the devices in the telemetry station may malfunction and cause errors in the data, which can result in false alarms or missed true alarms. Finding these errors requires experienced humans with specialised knowledge, which is very time-consuming and also inconsistent. Thus, there is a need to develop an automated approach. In this paper, we firstly investigated the applicability of Deep Reinforcement Learning (DRL). The testing results show that whilst they are more accurate than some other machine learning models, particularly in identifying unknown anomalies, they lacked consistency. Therefore, we proposed an ensemble approach that combines DRL models to improve consistency and also accuracy. Compared with other models, including Multilayer Perceptrons (MLP) and Long Short-Term Memory (LSTM), our ensemble models are not only more accurate in most cases, but more importantly, more reliable.

Testing Differential Item Functioning Without Predefined Anchor Items Using Robust Regression

Differential item functioning (DIF) occurs when the probability of endorsing an item differs across groups for individuals with the same latent trait level. The presence of DIF items may jeopardize the validity of an instrument; therefore, it is crucial to identify DIF items in routine operations of educational assessment. While DIF detection procedures based on item response theory (IRT) have been widely used, a majority of IRT-based DIF tests assume predefined anchor (i.e., DIF-free) items. Not only is this assumption strong, but violations to it may also lead to erroneous inferences, for example, an inflated Type I error rate. We propose a general framework to define the effect sizes of DIF without a priori knowledge of anchor items. In particular, we quantify DIF by item-specific residuals from a regression model fitted to the true item parameters in respective groups. Moreover, the null distribution of the proposed test statistic using robust estimator can be derived analytically or approximated numerically even when there is a mix of DIF and non-DIF items, which yields asymptotically justified statistical inference. The Type I error rate and the power performance of the proposed procedure are evaluated and compared with the conventional likelihood-ratio DIF tests in a Monte Carlo experiment. Our simulation study has shown promising results in controlling Type I error rate and power of detecting DIF items. Even when there is a mix of DIF and non-DIF items, the true and false alarm rate can be well controlled when a robust regression estimator is used.

Subcritical escape waves in schooling fish.

Theoretical physics predicts optimal information processing in living systems near transitions (or pseudo-critical points) in their collective dynamics. However, focusing on potential benefits of proximity to a critical point, such as maximal sensitivity to perturbations and fast dissemination of information, commonly disregards possible costs of criticality in the noisy, dynamic environmental contexts of biological systems. Here, we find that startle cascades in fish schools are subcritical (not maximally responsive to environmental cues) and that distance to criticality decreases when perceived risk increases. Considering individuals’ costs related to two detection error types, associated to both true and false alarms, we argue that being subcritical, and modulating distance to criticality, can be understood as managing a trade-off between sensitivity and robustness according to the riskiness and noisiness of the environment. Our work emphasizes the need for an individual-based and context-dependent perspective on criticality and collective information processing and motivates future questions about the evolutionary forces that brought about a particular trade-off.

Reducing False Alarms and Alarm Fatigue from Pulse Oximeters in a Neonatal Care Unit: A Quality Improvement Study

Background: Pulse oximeters play a vital role in monitoring sick newborns, but majority of the times, their alarms are of little clinical significance. False alarms from pulse oximeters were frequent in our neonatal intensive care unit, causing desensitization of staff and inattention to clinically important alarms. Objectives: The objective of the study was to reduce the burden of false alarms and alarm fatigue. Methods: This was a quality improvement (QI) study. During the baseline phase, alarms for heart rate and SPO2 (percentage of oxygenated blood) were evaluated. Response to them within 30 s was checked. Major causes of false alarms were the movement of the newborns, inappropriate alarm limits, and loose probe. Fishbone chart was prepared, and Plan-Do-Study-Act (PDSA) model was designed using point of care quality improvement (POCQI) principles. During the first PDSA (implementation phase), the staff was trained to adjust alarm limits using the reference chart. A lecture on noise hazards, emphasis on muting the alarms, and advice to change probe site at beginning of their duty was given. In the second PDSA (sustenance phase), components of the first PDSA were strengthened by supportive supervision and guidance and the training of new staff. Results: Total 494, 329, and 162 alarms were observed during baseline, implementation, and sustenance phases, respectively. In the baseline phase majority, 364 (73.7%) were false alarms, which occurred at a frequency of 0.39 alarms/patient/h. More than one-third of the alarms were not responded timely. After QI, false alarms reduced to 214 (65%; 0.22 alarms/patient/h) and 100 (61.7%; 0.16 alarms/patient/h) in implementation and sustenance phases, respectively. Response to true alarms improved from 101 (77.7%) to 104 (90.4%) to 62 (100%) during the 3 phases consecutively. Conclusion: Frequent false alarms lead to desensitization of health care workers. POCQI principles can be a practical approach for reducing false alarms and improving alarm safety.

Integration of observed and model-derived groundwater levels in landslide threshold models in Rwanda

Abstract. The incorporation of specific regional hydrological characteristics in empirical statistical landslide threshold models has considerable potential to improve the quality of landslide predictions towards reliable early warning systems. The objective of this research was to test the value of regional groundwater level information, as a proxy for water storage fluctuations, to improve regional landslide predictions with empirical models based on the concept of threshold levels. Specifically, we investigated (i) the use of a data-driven time series approach to model the regional groundwater levels based on short duration monitoring observations and (ii) the predictive power of single variable and bilinear threshold landslide prediction models derived from groundwater levels and precipitation. Based on statistical measures of the model fit (R2 and RMSE), the groundwater level dynamics estimated by the transfer function noise time series model are broadly consistent with the observed groundwater levels. The single variable threshold models derived from groundwater levels exhibited the highest landslide prediction power with 82 %–93 % of true positive alarms despite the quite high rate of false alarms with about 26 %–38 %. The further combination as bilinear threshold models reduced the rate of false alarms by about 18 %–28 % at the expense of reduced true alarms by about 9 %–29 % and is thus less advantageous than single variable threshold models. In contrast to precipitation-based thresholds, relying on threshold models exclusively defined using hydrological variables such as groundwater can lead to improved landslide predictions due to their implicit consideration of long-term antecedent conditions until the day of landslide occurrence.

Evaluating the performance of temporal and spatial early warning statistics of algal blooms.

Regime shifts have large consequences for ecosystems and the services they provide. However, understanding the potential for, causes of, proximity to, and thresholds for regime shifts in nearly all settings is difficult. Generic statistical indicators of resilience have been proposed and studied in a wide range of ecosystems as a method to detect when regime shifts are becoming more likely without direct knowledge of underlying system dynamics or thresholds. These early warning statistics (EWS) have been studied separately but there have been few examples that directly compare temporal and spatial EWS in ecosystem-scale empirical data. To test these methods, we collected high-frequency time series and high-resolution spatial data during a whole-lake fertilization experiment while also monitoring an adjacent reference lake. We calculated two common EWS, standard deviation and autocorrelation, in both time series and spatial data to evaluate their performance prior to the resulting algal bloom. We also applied the quickest detection method to generate binary alarms of resilience change from temporal EWS. One temporal EWS, rolling window standard deviation, provided advanced warning in most variables prior to the bloom, showing trends and between-lake patterns consistent with theory. In contrast, temporal autocorrelation and both measures of spatial EWS (spatial SD, Moran's I) provided little or no warning. By compiling time series data from this and past experiments with and without nutrient additions, we were able to evaluate temporal EWS performance for both constant and changing resilience conditions. True positive alarm rates were 2.5-8.3 times higher for rolling window standard deviation when a lake was being pushed towards a bloom than the rate of false positives when it was not. For rolling window autocorrelation, alarm rates were much lower and no variable had a higher true positive than false positive alarm rate. Our findings suggest temporal EWS provide advanced warning of algal blooms and that this approach could help managers prepare for and/or minimize negative bloom impacts.

Provable GPU Data-Races in Static Race Detection

We extend the theory behind the Faial tool-chain, which can soundly prove that CUDA programs (aka, kernels) are data-race free using specialized behavioral types called memory access protocols (MAPs). In this paper we extend the theory of MAPs to characterize kernels for which alarms can be identified as true alarms. We introduce a core calculus for CUDA, which we named BabyCUDA, and a behavioral type system for it. We show that if a BabyCUDA program can be assigned a MAP, then any alarm raised by Faial for this program is a true alarm.

A contrastive learning approach for\xa0ICU false arrhythmia\xa0alarm reduction

The high rate of false arrhythmia alarms in Intensive Care Units (ICUs) can lead to disruption of care, negatively impacting patients’ health through noise disturbances, and slow staff response time due to alarm fatigue. Prior false-alarm reduction approaches are often rule-based and require hand-crafted features from physiological waveforms as inputs to machine learning classifiers. Despite considerable prior efforts to address the problem, false alarms are a continuing problem in the ICUs. In this work, we present a deep learning framework to automatically learn feature representations of physiological waveforms using convolutional neural networks (CNNs) to discriminate between true vs. false arrhythmia alarms. We use Contrastive Learning to simultaneously minimize a binary cross entropy classification loss and a proposed similarity loss from pair-wise comparisons of waveform segments over time as a discriminative constraint. Furthermore, we augment our deep models with learned embeddings from a rule-based method to leverage prior domain knowledge for each alarm type. We evaluate our method using the dataset from the 2015 PhysioNet Computing in Cardiology Challenge. Ablation analysis demonstrates that Contrastive Learning significantly improves the performance of a combined deep learning and rule-based-embedding approach. Our results indicate that the final proposed deep learning framework achieves superior performance in comparison to the winning entries of the Challenge.

Human Activity and Motion Pattern Recognition within Indoor Environment Using Convolutional Neural Networks Clustering and Naive Bayes Classification Algorithms.

Human Activity Recognition (HAR) systems are designed to read sensor data and analyse it to classify any detected movement and respond accordingly. However, there is a need for more responsive and near real-time systems to distinguish between false and true alarms. To accurately determine alarm triggers, the motion pattern of legitimate users need to be stored over a certain period and used to train the system to recognise features associated with their movements. This training process is followed by a testing cycle that uses actual data of different patterns of activity that are either similar or different to the training data set. This paper evaluates the use of a combined Convolutional Neural Network (CNN) and Naive Bayes for accuracy and robustness to correctly identify true alarm triggers in the form of a buzzer sound for example. It shows that pattern recognition can be achieved using either of the two approaches, even when a partial motion pattern is derived as a subset out of a full-motion path.

Why Do Birds False Alarm Flight?

False alarm flighting in avian flocks is common, and has been explained as a maladaptive information cascade. If false alarm flighting is maladaptive per se, then its frequency can only be explained by it being net adaptive in relation to some other benefit or equilibrium. However, I argue that natural selection cannot distinguish between false and true alarm flights that have similar energetic costs, opportunity costs, and outcomes. False alarm flighting cannot be maladaptive if natural selection cannot perceive the difference between true and false alarm flighting. Rather, the question to answer is what false and true alarm flighting both have in common that is adaptive per se. The fire drill hypothesis of alarm flighting posits that false alarm flights are an adaptive investment in practicing escape. The fire drill hypothesis predicts that all individuals can benefit from practicing escape, particularly juveniles. Flighting practice could improve recognition of and response time to alarm flighting signals, could compensate for inter-individual and within-day weight differences, and could aid the development of adaptive escape tactics. Mixed-age flocks with many juveniles are expected to false alarm flight more than adult flocks. Flocks that inhabit complex terrain should gain less from escape practice and should false alarm flight less. Behavioural ecology framings can be fruitfully complemented by other research traditions of learning and behaviour that are more focused on maturation and motor learning processes.

Evaluation of the Coastal Acoustic Buoy for offshore wind for real time mitigation of North Atlantic right whales

A recent Incidental Harassment Authorization requires a 10 km zone to be monitored with passive acoustics before and during pile driving. SMRU Consulting has built the Coastal Acoustic Buoy for Offshore Wind (CABOW) to address this need. Each CABOW consists of: a bottom lander with three hydrophones; data acquisition system; and onboard computer running PAMGuard. The CABOW detects potential calls and relays clips to a base station for classification, bearing estimation, and validation. Bench testing characterized detector performance and measured bearing accuracy as a function of SNR. Field trials used playbacks of real and simulated right whale upcalls to evaluate the detection probability with respect to the range and signal excess of the call; estimate bearing accuracy; and test the range and stability of the radio communications. Field trials indicated a maximum detection range of 4–12 km under high and very low noise levels, respectively. Finally, we used a simulation to compare true and false alarm rates of the CABOW to an equivalent single sensor system for monitoring a fixed area. Simulations show that incorporating bearings to calling animals could provide a substantial improvement in false alarm rates relative to single sensors if properly placed with respect to potential noise sources.

A predictive model incorporating the change detection and Winsorization methods for alerting hypoglycemia and hyperglycemia.

This paper focuses on establishing an effective predictive model to quickly and accurately alert hypoglycemia and hyperglycemia for helping control blood glucose levels of people with diabetes. In general, a good predictive model is established on the features of data. Inspired by this, we first analyze the characteristics of continuous glucose monitoring (CGM) data by the equality of variances test and outlier detection, which show time-varying fluctuations and jump points in CGM data. Therefore, we incorporate the change detection method and the Winsorization method into the predictive model based on the autoregressive moving average (ARMA) model and the recursive least squares (RLS) method to fit the above characteristics. To the best of our knowledge, the proposed method is the first attempt to give a solution for matching the time-varying fluctuations and jump points of CGM data simultaneously. A case study using CGM data is given to validate the effectiveness of the proposed method under 30-min-ahead prediction. The results show that the proposed method can improve the true alarm ratio of hypoglycemia and hyperglycemia from 0.7983 to 0.8783, and lengthen the average advance detection time of hypoglycemia and hyperglycemia from 19.77 to 22.64min.

Simulating Study Design Choice Effects on Observed Performance of Predictive Patient Monitoring Alarm Algorithms.

There are multiple study design choices to be selected in order to perform evaluations of predictive patient monitoring algorithms related to the event and true positive alarm definitions (e.g., how far ahead of the event is a true positive alarm). Often, passively collected patient monitoring datasets from clinical environments are available to perform these types of studies, so that the effects of different study design choices can be simulated to evaluate the robustness of an algorithm to those choices. Here, we simulate the effects of varying alarm and event definition criteria on the reported performance of the early warning score to predict hypotensive events. A total of 432 combinations of study design choices were simulated. Area under the receiver-operating characteristic curve varied from greater than 0.8 to less than 0.5 by adjusting alarm and event definition criteria. Traditional metrics for evaluating diagnostic systems were modulated across a wide range by adjusting study design choices for a predictive algorithm using a patient monitoring dataset. This highlights the importance of examining study design choices for new predictive patient monitoring algorithms and presents an approach to simulate different study designs with retrospective patient monitoring data as part of a robustness evaluation.

A new time adjusting control limits chart for concept drift detection

Time varying dynamic systems whose underlying changing distribution should be continuously monitored to track abnormal behaviors are one of the most recent challenges in many practical applications. When the data arrive in a continuous way, the target concept to be monitored may change accordingly causing a problem of concept drift. Thus, distinguishing between true alarms and changes due to the nonstationarity of the loading data is required. Traditional control charts cannot handle such processes since they do not use a change dependent procedure and they are not designed for concept drift problems. This article proposes the first two-stage time adjusting control chart for monitoring data stream processes with concept drift. Stage I updates the control limits each time an adjustment condition is satisfied based on an incremental linear combination of the historical and the new data. Stage II validates the shift detected in Stage I by testing whether the two subsamples around the drift belong to the same distribution. Experiments based on several drift situations and using different performance measures show that the proposed adaptive chart is more robust than the most recent competitive time varying charts existing in the literature. Moreover, it is more efficient in terms of shift recognition by reducing the false negative detections in several cases.

Feature Design Assessment of the Ship Fire Alarm System

Damages and misfortunes caused by fire on ships have recently accelerated the creation of new approaches, development, and building the security and unchanging quality of the fire detection framework. Simultaneously, with the growing interest in better early fire detection and prevention, numerous frameworks are being created for the detection of progress, with control calculations having the task of carefully preparing and identifying true/false signals from fire or flames or the true alarm from false alarms. By utilizing the assistance provided by innovation, transport owners are more likely to service groups and fleets of ships and reduce potential fire accident costs. This article provides an overview of recent methodologies and technology for early detection of ship fires, as well as an enhanced approach for evaluating the Human-Machine-Interface (HMI) function of an alarming ship using a machine operating simulator called DMS-2017B. The DMS-2017B machinery operation simulator can unify the noise environment to avoid the influence of environmental differences on cabin experimental results. Compared to conventional Binomial Testing, a ship simulator coupled with the theory of affordance that provides a more realistic and operable way to assess the feature design of ship fire alarm and the threshold of some influence factors can also be used. According to the quantitative analysis of experimental results based on the ordered logit model, the function of the ship fire alarm would be improved significantly by adding recorded broadcasting and replacing static symbols with flashing symbols. Increasing sound pressure is also an effective way of doing this, but an auditory threshold is present. Above 75 dB, this effect will fade down, along with noise pollution. However, the effect difference between continuous alarm and square wave pulse alarm is negligible. The conclusion can provide some guidance for the design of a ship fire alarm. An appropriate design is expected to facilitate the efficiency of handling accidents and guiding evacuation.

Real-time machine learning-based intensive care unit alarm classification without prior knowledge of the underlying rhythm.

AimsThis work attempts to develop a standalone heart rhythm alerting system for the intensive care unit (ICU), where life-threatening arrhythmias have to be identified/alerted more precisely and more instantaneously (i.e. with lower latency) than existing bedside monitors. Methods and resultsWe use the dataset from the PhysioNet 2015 Challenge, which contains records that led to true and false arrhythmic alarms in the ICU. These records have been re-annotated as one of eight classes, namely (i) asystole, (ii) extreme bradycardia, (iii) extreme tachycardia, (iv) ventricular fibrillation (VF), (v) ventricular tachycardia (VT), (vi) normal sinus rhythm, (vii) sinus tachycardia, and (viii) noise/artefacts. Arrhythmia-specific features and features that measure the signal quality were extracted from all the records. To improve VF detection, an improved, over an existing, single-lead R-wave detection was developed that takes into account the R-waves detected in all electrocardiographic (ECG) leads. To avoid false R-wave detection due to pacing spikes, ECG signals were filtered with a low pass filter prior to R-wave detection, while the raw signals were used for feature extraction. Random forest was used as the classifier, and 10-time five-fold cross-validation, resulted in a macro-average sensitivity of 81.54%.ConclusionsIn conclusion, comparing with the bedside monitors used in the PhysioNet 2015 competition, we find that our method achieves higher positive predictive values for asystole, extreme bradycardia, VT, and VF; furthermore, our method is able to alert the presence of arrhythmia instantaneously, i.e. up to 4 s earlier.

Comparing malaria early detection methods in a declining transmission setting in northwestern Ethiopia

BackgroundDespite remarkable progress in the reduction of malaria incidence, this disease remains a public health threat to a significant portion of the world’s population. Surveillance, combined with early detection algorithms, can be an effective intervention strategy to inform timely public health responses to potential outbreaks. Our main objective was to compare the potential for detecting malaria outbreaks by selected event detection methods.MethodsWe used historical surveillance data with weekly counts of confirmed Plasmodium falciparum (including mixed) cases from the Amhara region of Ethiopia, where there was a resurgence of malaria in 2019 following several years of declining cases. We evaluated three methods for early detection of the 2019 malaria events: 1) the Centers for Disease Prevention and Control (CDC) Early Aberration Reporting System (EARS), 2) methods based on weekly statistical thresholds, including the WHO and Cullen methods, and 3) the Farrington methods.ResultsAll of the methods evaluated performed better than a naïve random alarm generator. We also found distinct trade-offs between the percent of events detected and the percent of true positive alarms. CDC EARS and weekly statistical threshold methods had high event sensitivities (80–100% CDC; 57–100% weekly statistical) and low to moderate alarm specificities (25–40% CDC; 16–61% weekly statistical). Farrington variants had a wide range of scores (20–100% sensitivities; 16–100% specificities) and could achieve various balances between sensitivity and specificity.ConclusionsOf the methods tested, we found that the Farrington improved method was most effective at maximizing both the percent of events detected and true positive alarms for our dataset (> 70% sensitivity and > 70% specificity). This method uses statistical models to establish thresholds while controlling for seasonality and multi-year trends, and we suggest that it and other model-based approaches should be considered more broadly for malaria early detection.