Risk Of False Alarms Research Articles

Impact of Time-Correlation of Monitor Statistic on Continuity of Safety-Critical Operations

Integrity monitors are an essential component of ensuring the quality of navigation measurements for safety-critical GNSS augmentation systems. The sensitivity of these monitors is closely related to requirements limiting monitor false alarms. This paper shows that the risk of false alarms interrupting safety critical operations (loss of continuity) is closely tied to monitor-noise correlation. Analysis shows that specific continuity risk may be as high as 50% for conventional monitor implementations, when time correlation is considered. This paper presents an alternate two-threshold monitor implementation, which features both a subcritical threshold and a critical threshold, only the latter of which triggers a loss of continuity. Using this two-threshold implementation, we introduce methods to compute specific continuity risk in the presence of time-correlated noise. Subsequently, through simulation, we quantify how specific continuity risk is influenced by varying levels of time-correlation, which may be present in the raw monitor data or introduced by smoothing. Copyright © 2012 Institute of Navigation.

Detecting outliers in multivariate data while controlling false alarm rate

Outlier identification often implies inspecting each z-transformed variable and adding a Mahalanobis D 2 . Multiple outliers may mask each other by increasing variance estimates. Caroni & Prescott (1992) proposed a extension of Rosner’s (1983) technique to circumvent masking, taking sample size into account to keep the false alarm risk below, say, α = .05. Simulations studies here compare the single approach to multiple-univariate plus multivariate tests, each at a Bonferroni corrected α level, in terms of power at detecting outliers. Results suggest the former is better only up to about 12 variables. Macros in an Excel spreadsheet implement these techniques. The impetus of the present work was to identify, in the context of a graduate course in statistics, sound statistical procedures to recommend for the examination of data for the detection of outliers, assuming normal distributions . The basic consideration is that the statistical criterion beyond which a piece of data would be considered an outlier must take into account both the number of cases (subjects) inspected as well as the number of variables examined if the variables are inspected one by one. This is required to adequately control the risk of falsely rejecting at least one case that actually belongs to the population. In particular, a fixed critical z-score, irrespective of number of variables or of sample size, can hardly be recommended. Beyond controlling for false alarm (FA) rate,

Limits to the detection of early warning signals of population collapse

Abstract Background/Question/Methods The recog-ni-tion that ecosys-tems can undergo sud-den shifts to alter-nate, less desir-able sta-ble states has led to the desire to iden-tify early warn-ing signs of these impend-ing col-lapses. This search has been moti-vated by the math-e-mat-ics of bifur-ca-tions, in which sud-den shifts result not from direct per-tur-ba-tions to the state (i.e. the pop-u-la-tion abun-dance, through mech-a-nisms such as over-harvesting) but to a slowly chang-ing para-me-ter that impacts the sys-tem sta-bil-ity. While these col-lapses can-not be antic-i-pated by observ-ing only the mean dynam-ics (as described by a deter-min-is-tic model), signs of the impend-ing col-lapse are expressed in the ran-dom per-tur-ba-tions, or noise, inher-ent in real sys-tems. The math-e-mat-i-cal the-ory of early warn-ing signs exploits this fact by seek-ing to detect pat-terns such as “crit-i-cal slow-ing down” of these per-tur-ba-tions due to the grad-ual loss of sta-bil-ity which leads to a bifurcation.While much atten-tion has been given to empha-siz-ing the exis-tence both of sud-den col-lapses and of signs of crit-i-cal slow-ing down, lit-tle atten-tion has been paid to its detec-tion. Faced with only finite data, any method risks both false alarms and failed detec-tion events. We believe that weigh-ing these risks must be the bur-den of man-age-ment pol-icy, while research must first pro-vide a reli-able way to quan-tify the rel-a-tive risks of each. We present a method which quan-ti-fies this risk and show how to decrease the uncer-tainty inher-ent in com-mon summary-statistic approaches through the use of a like-li-hood based mod-el-ing approach. Results/Conclusions We demon-strate that com-monly used cor-re-la-tion tests applied to sum-mary sta-tis-tics such as auto-cor-re-la-tion and vari-ance are both inap-pro-pri-ate and insuf-fi-cient tests of early warn-ing signals.Our method esti-mates directly the para-me-ters of a gen-er-al-ized model of the bifur-ca-tion pos-tu-lated by early warn-ing sig-nals the-ory, with and with-out the pres-ence of a grad-ual change lead-ing towards col-lapse. Using Monte Carlo sim-u-la-tion we gen-er-ate the dis-tri-b-u-tion of warning-signal sta-tis-tics expected under each model. From this we can quan-tify the risk of false alarms and missed detec-tion. We then show how apply-ing this approach to the data directly rather than the sum-mary sta-tis-tic increases the power of detec-tion. We illus-trate the approach in both sim-u-lated and empir-i-cal data of sud-den eco-log-i-cal shifts.

Limits to the detection of early warning signals of population collapse

Background/Question/MethodsThe recog-ni-tion that ecosys-tems can undergo sud-den shifts to alter-nate, less desir-able sta-ble states has led to the desire to iden-tify early warn-ing signs of these impend-ing col-lapses. This search has been moti-vated by the math-e-mat-ics of bifur-ca-tions, in which sud-den shifts result not from direct per-tur-ba-tions to the state (i.e. the pop-u-la-tion abun-dance, through mech-a-nisms such as over-harvesting) but to a slowly chang-ing para-me-ter that impacts the sys-tem sta-bil-ity. While these col-lapses can-not be antic-i-pated by observ-ing only the mean dynam-ics (as described by a deter-min-is-tic model), signs of the impend-ing col-lapse are expressed in the ran-dom per-tur-ba-tions, or noise, inher-ent in real sys-tems. The math-e-mat-i-cal the-ory of early warn-ing signs exploits this fact by seek-ing to detect pat-terns such as “crit-i-cal slow-ing down” of these per-tur-ba-tions due to the grad-ual loss of sta-bil-ity which leads to a bifurcation.While much atten-tion has been given to empha-siz-ing the exis-tence both of sud-den col-lapses and of signs of crit-i-cal slow-ing down, lit-tle atten-tion has been paid to its detec-tion. Faced with only finite data, any method risks both false alarms and failed detec-tion events. We believe that weigh-ing these risks must be the bur-den of man-age-ment pol-icy, while research must first pro-vide a reli-able way to quan-tify the rel-a-tive risks of each. We present a method which quan-ti-fies this risk and show how to decrease the uncer-tainty inher-ent in com-mon summary-statistic approaches through the use of a like-li-hood based mod-el-ing approach.Results/ConclusionsWe demon-strate that com-monly used cor-re-la-tion tests applied to sum-mary sta-tis-tics such as auto-cor-re-la-tion and vari-ance are both inap-pro-pri-ate and insuf-fi-cient tests of early warn-ing signals.Our method esti-mates directly the para-me-ters of a gen-er-al-ized model of the bifur-ca-tion pos-tu-lated by early warn-ing sig-nals the-ory, with and with-out the pres-ence of a grad-ual change lead-ing towards col-lapse. Using Monte Carlo sim-u-la-tion we gen-er-ate the dis-tri-b-u-tion of warning-signal sta-tis-tics expected under each model. From this we can quan-tify the risk of false alarms and missed detec-tion. We then show how apply-ing this approach to the data directly rather than the sum-mary sta-tis-tic increases the power of detec-tion. We illus-trate the approach in both sim-u-lated and empir-i-cal data of sud-den eco-log-i-cal shifts.

Funnel plots for comparing provider performance based on patient-reported outcome measures

BackgroundPatient-reported outcome measures (PROMs) often produce skewed distributions of individual scores after a healthcare intervention. For health performance indicators derived from skewed distributions, funnel plots designed with symmetric control limits...

Enhancement of the neural network modeling accuracy using a submodeling decomposition-based technique, application in gas sensor

This paper presents an algorithm based on the use of artificial neural networks (ANNs) in order to reduce the processing time and to improve the accuracy in ANN modeling, which can be accomplished with a division of the model to submodels by input subintervals. We apply this method with a gas sensor aiming to accurately control the small gas leaks, thus decreasing the risk of false alarms and missed detections. The sensor model accurately, especially in small concentrations, expresses the nonlinear character of the response and the dependence on temperature and relative humidity in addition to the gas nature dependency. The corrector linearizes and compensates the sensor’s responses. The results obtained show the effectiveness of the proposed technique.

Control charts for individual observations of a bivariate Poisson process

In this paper, three single-control charts are proposed to monitor individual observations of a bivariate Poisson process. The specified false-alarm risk, their control limits, and ARLs were determined to compare their performances for different types and sizes of shifts. In most of the cases, the single charts presented better performance rather than two separate control charts (one for each quality characteristic). A numerical example illustrates the proposed control charts.

Moving Object Detection for Real Time Video Surveillance: An Edge Based Approach

SUMMARY This paper presents an automatic edge segment based algorithm for the detection of moving objects that has been specially developed to deal with the variations in illumination and contents of background. We investigated the suitability of the proposed edge segment based moving object detection algorithm in comparison with the traditional intensity based as well as edge pixel based detection methods. In our method, edges are extracted from video frames and are represented as segments using an efficiently designed edge class. This representation helps to obtain the geometric information of edge in the case of edge matching and shape retrieval; and creates effective means to incorporate knowledge into edge segment during background modeling and motion tracking. An efficient approach for background edge generation and a robust method of edge matching are presented to effectively reduce the risk of false alarm due to illumination change and camera motion while maintaining the high sensitivity to the presence of moving object. The proposed method can be successfully realized in video surveillance applications in home networking environment as well as various monitoring systems. As, video coding standard MPEG-4 enables content based functionality, it can successfully utilize the shape information of the detected moving objects to achieve high coding efficiency. Experiments with real image sequences, along with comparisons with some other existing methods are presented, illustrating the robustness of the pro

Edge Segment-Based Automatic Video Surveillance

This paper presents a moving-object segmentation algorithm using edge information as segment. The proposed method is developed to address challenges due to variations in ambient lighting and background contents. We investigated the suitability of the proposed algorithm in comparison with the traditional-intensity-based as well as edge-pixel-based detection methods. In our method, edges are extracted from video frames and are represented as segments using an efficiently designed edge class. This representation helps to obtain the geometric information of edge in the case of edge matching and moving-object segmentation; and facilitates incorporating knowledge into edge segment during background modeling and motion tracking. An efficient approach for background initialization and robust method of edge matching is presented, to effectively reduce the risk of false alarm due to illumination change and camera motion while maintaining the high sensitivity to the presence of moving object. Detected moving edges are utilized along with watershed algorithm for extracting video object plane (VOP) with more accurate boundary. Experiment results with real image sequence reflect that the proposed method is suitable for automated video surveillance applications in various monitoring systems.

Non-normality and the variable parameters [formula omitted] control charts

Recent studies has demonstrated the adaptive (i.e., variable sample sizes, sampling intervals, and/or action limit coefficients) X ¯ charts are quicker than standard Shewhart (SS) X ¯ control chart in detecting process mean shifts. The usual assumption for designing a control chart is that the data or measurements are normally distributed. However, this assumption may not be true for some processes. In this paper, the performance of the adaptive X ¯ chart is evaluated under non-normality. Based on the study, it is shown that the variable parameters (VP) X ¯ chart is more effective than the other adaptive control charts in detecting small process mean shifts under non-normality. More importantly, the risk of false alarm of the VP X ¯ chart can be substantially decreased.

Robustness of the Variable Sample Size and Control Limit ¯X Chart to Non Normality

Recent studies demonstrated that the variable sample size (VSS) ¯X chart is quicker than the standard Shewhart (SS) ¯X chart in detecting small process mean shifts. The usual assumption for designing a control chart is that the data or measurements are normally distributed. However, this assumption may not be tenable in some production processes. The Burr distribution has been used in the literature to represent various non normal distributions. In this article, the Burr distribution will be employed to evaluate the control charts for non normal populations. We first show the VSS and Shewhart ¯X charts are sensitive to non normality. Then we propose a method of varying the sample size and the control limits simultaneously. The variable sample size and control limit VSSCL ¯X chart is shown to be quicker than the VSS ¯X chart in detecting small and moderate shifts in the process. Most importantly, the risk of false alarm for the VSSCL ¯X chart can be substantially decreased. In addition, with proper selection of chart parameters, the VSSCL ¯X chart is more robust to non normality than the VSS and Shewhart ¯X charts.

Evaluation of environmental monitoring strategies.

In environmental monitoring, it is important that the monitoring system should emit early warnings when undesired events occur. These events may be sudden or of a more subtle nature. In the design of such monitoring systems, a proper balance between cost and risk must be achieved. There are 2 classic types of risk connected with early warning systems, namely the risk of not detecting significant changes and the risk of false alarms. The purpose of this paper is to describe a method for comparing the performance of different monitoring systems, considering the classic types of risk and cost. The method is applied to the monitoring of the lichen cover as a test case. The expected utility has been used as a measure of performance. When estimating the probabilities of the events, spatial microsimulation and Monte-Carlo simulation techniques have been used. The monitoring programs studied are based on satellite images, aerial photos, field samples, and land-cover maps. The major conclusions of this study are that standardized quality measures are extremely useful for evaluating the usability of environmental monitoring methods. In addition, when estimating gains and costs, spatial microsimulation techniques are useful. To improve the method, however, macroconstraints should also be used for aligning the simulation model.

Signs of potential renewal of eruptive activity at La Fossa (Vulcano, Aeolian Islands)

Since the end of the last magmatic eruption (1890), activity of La Fossa (southern Tyrrhenian Sea, Italy) has consisted of fumarolic emissions of fluctuating intensity. Fluids are discharged principally at two fumarolic fields located in the northern rim of the active crater and at the beach sited at its northern foot. Increased thermal, seismic and geochemical activity has been recorded since 1978, when an earthquake of M=5.5 occurred in the region. This paper combines available geophysical and geochemical information in order to develop a tentative interpretation of two episodes of apparent unrest which occurred in 1985 and 1987–1988, enhancing the risk of renewal of the eruptive activity. The 1985 unrest consisted essentially of a sharp build up of the internal pressure in the shallow hydrothermal system, which was induced by the injection of hot gases of magmatic origin. The crater fumaroles displayed significant increases in CO2 and other acid species, but their outlet temperature did not change. Conversely, the 1987–1988 episode was characterized by appreciable modifications at the crater fumaroles, with only secondary effects at the fumarole system of the beach. The sliding of part of the eastern flank of the La Fossa cone into the sea occurred on 20 April 1988, when the region was affected by crustal dilatation producing a seismic sequence of relatively high intensity. Both episodes of unrest were accompanied by increases of local microseismic activity, which affected the nothern sector of the island in 1985, and the southern one in 1988. Finally, a phase of appreciable areal contraction was detected in 1990, probably due to the effect of the cooling and crystallization of magma at relatively shallow depths, accompanying the increased thermal activity at the crater fumaroles. Regional tectonic stress seems to play an important role in the transition of the volcanic system from a phase of relative stability to a phase of apparent unrest, inducing the heating and the expansion of shallow hydrothermal fluids. Available information is insufficient to indicate whether or not the volcano is building towards the renewal of a magmatic eruption, and there is no evidence to hypothesize episodes of significant magma migration. The frequency of measurements of many parameters needs to be increased in order to learn more about the temporal relationships between geochemical and geophysical variations preceding and accompanying periods of increased thermal activity. This will probably be a valid tool for recognizing short-term precursors of a future eruption, reducing the risk of false alarms.

THE EFFECT OF PRESSURE ON PORTABLE GAS MONITORING EQUIPMENT DURING COMPRESSED AIR TUNNELLING

Three commercially available portable multi-gas monitors were operated side-by-side in a pressurized tunnel and their performance assessed. Simultaneously ambient conditions in the tunnel (temperature, pressure and humidity) were also measured, and from these data ambient events leading to spurious behaviour by the monitors identified. The results show that pressure, both constant and transient, can, in some instances, affect the performance of the monitors. For example, transient changes of pressure affects the oxygen sensors, causing signal spikes and increasing the risk of false alarms. Also, constant pressure can in some instances cause a zero shift on some sensors, and this can be negative so that the sensor under-reads. The paper goes on to discuss these anomalies and gives guidance on how to overcome them and reduce the risk of false alarms. If this guidance is implemented, the work here suggests that these monitors can provide warning of flammable and toxic hazards as well as of oxygen deficiency or enrichment.

Radar satellites: A new tool for pollution monitoring in coastal waters

Radar satellites are currently being used on a routine basis for near real‐time pollution monitoring in Norwegian waters. This article describes the phased introduction of this service, from infrastructure development, basic science, and field experiments, to near real‐time demonstrations and knowledge transfer from research laboratories to operational entities. The service is initially based on the European Space Agency's ERS satellites. Future radar satellites such as RADARSAT‐1 and ENVISAT‐1 will offer increased coverage. At low wind speed (3–4 m/s) even very thin pollutants can be detected, but there is a risk of false alarms from slicks of natural origin. Emulsion oil has been observed with ERS‐1 at 10 m/s wind speed.

Gas sensing for fire detection: Measurements of CO, CO 2, H 2, O 2, and smoke density in European standard fire tests

Measurements were made of the concentration of various gases during the course of six types of fire that conform to the British Standard BS 5445 part 9 (which is identical to the European Standard CEN- 54). It is shown that a ‘chemical fire detector’ that has good performance in all of the six test fires could be made by the measurement of certain gases. In addition, analysis of the output from the various signals could provide further information about the state of, and type of, fire, thereby reducing the risk of false alarms. The use of a chemical fire detector could therefore improve current fire detection systems.

An earthquake alarm system for the Maui A Offshore Platform, New Zealand

abstract An earthquake alarm system for the Maui A Offshore Platform, which is situated in the Tasman Sea off the coast of New Zealand for the production of natural gas, is described. The function of the alarm system is to give an immediate warning when accelerations equal to half the design level for the platform have been reached in order that safety procedures can be initiated. The alarm system was designed to monitor only the response of the lower modes of the platform, as these would make the major contribution to the stresses in the platform. Ambient vibration measurements were performed which showed the values of frequency for the six lowest modes to be in the range of 0.45 to 1.35 Hz. The alarm system was accordingly designed so that the signal from the transducers passed through a filter with a nominally flat frequency response over a bandwidth 0.3 to 2 Hz with a sharp roll-off at 24 dB per octave at higher frequencies. A radio link with similar detectors on shore was arranged to give confirmation that an earthquake had occurred in order to reduce the risk of false alarms.