Large Number Of False Alarms Research Articles

Effects of display design on signal detection in flash flood forecasting

The Flooded Locations and Simulated Hydrographs (FLASH) project is a suite of tools that use weather radar-based rainfall estimates to force hydrologic models to predict flash floods in real-time. However, early evaluation of FLASH tools in a series of simulated forecasting operations, it was believed that the data aggregation and visualization methods might have contributed to forecasting a large number of false alarms. The present study addresses the question of how two alternative data aggregation and visualization methods affect signal detection of flash floods. A sample of 30 participants viewed a series of stimuli created from FLASH images and were asked to judge whether or not they predicted significant or insignificant amounts of flash flooding. Analyses revealed that choice of aggregation method did affect probability of detection. Additional visual indicators such as geographic scale of the stimuli and threat level affected the odds of interpreting the model predictions correctly as well as congruence in responses between national and local scale model outputs.

Reduction of false arrhythmia alarms using signal selection and machine learning

In this paper, we propose an algorithm that classifies whether a generated cardiac arrhythmia alarm is true or false. The large number of false alarms in intensive care is a severe issue. The noise peaks caused by alarms can be high and in a noisy environment nurses can experience stress and fatigue. In addition, patient safety is compromised because reaction time of the caregivers to true alarms is reduced.The data for the algorithm development consisted of records of electrocardiogram (ECG), arterial blood pressure, and photoplethysmogram signals in which an alarm for either asystole, extreme bradycardia, extreme tachycardia, ventricular fibrillation or flutter, or ventricular tachycardia occurs. First, heart beats are extracted from every signal. Next, the algorithm selects the most reliable signal pair from the available signals by comparing how well the detected beats match between different signals based on -score and selecting the best match. From the selected signal pair, arrhythmia specific features, such as heart rate features and signal purity index are computed for the alarm classification. The classification is performed with five separate Random Forest models. In addition, information on the local noise level of the selected ECG lead is added to the classification. The algorithm was trained and evaluated with the PhysioNet/Computing in Cardiology Challenge 2015 data set. In the test set the overall true positive rates were 93 and 95% and true negative rates 80 and 83%, respectively for events with no information and events with information after the alarm. The overall challenge scores were 77.39 and 81.58.

Robust Complex Behaviour Modeling at 90Hz

Modeling complex crowd behaviour for tasks such as rare event detection has received increasing interest. However, existing methods are limited because (1) they are sensitive to noise often resulting in a large number of false alarms; and (2) they rely on elaborate models leading to high computational cost thus unsuitable for processing a large number of video inputs in real-time. In this paper, we overcome these limitations by introducing a novel complex behaviour modeling framework, which consists of a Binarized Cumulative Directional (BCD) feature as representation, novel spatial and temporal context modeling via an iterative correlation maximization, and a set of behaviour models, each being a simple Bernoulli distribution. Despite its simplicity, our experiments on three benchmark datasets show that it significantly outperforms the state-of-the-art for both temporal video segmentation and rare event detection. Importantly, it is extremely efficient — reaches 90Hz on a normal PC platform using MATLAB.

Prevalence of Alarms in Intensive Care Units, and its Relationship with Nursing Staff Levels

Background: The average number of alarms per patient on each day in Intensive Care Unit (ICU) was very high with poor specificity, high sensitivity and high false positive rate. The large number of false alarms has caused healthcare professionals to turn down the volume of audible signals, adjust the alarm setting beyond limits that are safe and appropriate for the patient, and ignore or even deactivate alarms, resulting in sentinel events and patient deaths. The objectives of the present study were to examine the prevalence of ICU cardiac and technical alarms and the relationship between that prevalence and available nursing staff levels. Methods: The study collected all cardiac and technical alarm data from the bedside physiological monitor through the central monitoring system at the nurses' station, over a five-week period. The prevalence of these alarms and the correlation with different shifts of duty was analysed. The relationship between nursing staff levels and the number of these alarms was also analysed. Results: There was a positive correlation between the number of cardiac and technical alarms per bed per hour in three different shifts (Night and Morning, Morning and Afternoon, and, Afternoon and Night: All p-value<0.001). The effect of these alarms on the present shift will affect the number of alarms in the subsequent three shifts. Besides, the number of cardiac and technical alarms is not related to the nursing staff levels. Conclusions: This study describes the prevalence of cardiac and technical alarms from a different perspective, by examining the prevalence of physiological monitor cardiac and technical alarms in ICUs (but not their sound amplitude) and its relationship with nursing staff levels, the finding against many people thinking that the cardiac and technical alarms should be fewer when the nursing staffing level is high in the unit.

PMHT Approach for Multi-Target Multi-Sensor Sonar Tracking in Clutter.

Multi-sensor sonar tracking has many advantages, such as the potential to reduce the overall measurement uncertainty and the possibility to hide the receiver. However, the use of multi-target multi-sensor sonar tracking is challenging because of the complexity of the underwater environment, especially the low target detection probability and extremely large number of false alarms caused by reverberation. In this work, to solve the problem of multi-target multi-sensor sonar tracking in the presence of clutter, a novel probabilistic multi-hypothesis tracker (PMHT) approach based on the extended Kalman filter (EKF) and unscented Kalman filter (UKF) is proposed. The PMHT can efficiently handle the unknown measurements-to-targets and measurements-to-transmitters data association ambiguity. The EKF and UKF are used to deal with the high degree of nonlinearity in the measurement model. The simulation results show that the proposed algorithm can improve the target tracking performance in a cluttered environment greatly, and its computational load is low.

False alarm classification for multivariate manufacturing processes of thin film transistor–liquid crystal displays

Control charts have been widely used to improve manufacturing processes by reducing variations and defects. In particular, multivariate control charts have been effectively applied with monitoring processes that contain many correlated variables. Most existing multivariate control charts are vulnerable to misclassification errors that originate because of the hypothesis tests. In particular, these often cause the generation of a large number of false alarms. In this paper, we propose a procedure to reduce false alarms by combining a multivariate control chart and data mining algorithms. Simulation and real case studies demonstrate that the proposed method effectively reduces the false alarm rate.

Improvements of the shock arrival times at the Earth model STOA

AbstractPrediction of the shocks' arrival times (SATs) at the Earth is very important for space weather forecast. There is a well‐known SAT model, Shock Time of Arrival (STOA), which is widely used in the space weather forecast. However, the shock transit time from STOA model usually has a relative large error compared to the real measurements. In addition, STOA tends to yield too much “yes” prediction, which causes a large number of false alarms. Therefore, in this work, we work on the modification of STOA model. First, we give a new method to calculate the shock transit time by modifying the way to use the solar wind speed in STOA model. Second, we develop new criteria for deciding whether the shock will arrive at the Earth with the help of the sunspot numbers and the angle distances of the flare events. It is shown that our work can improve the SATs prediction significantly, especially the prediction of flare events without shocks arriving at the Earth.

SAR image target detection in complex environments based on improved visual attention algorithm

A novel target detection algorithm for synthetic aperture radar (SAR) images based on an improved visual attention method is proposed in this paper. With the development of SAR technology, target detection algorithms are confronted with many difficulties such as a complicated environment and scarcity of target information. Visual attention of the human visual system can make humans easily focus on key points in a complex picture, and the visual attention algorithm has been used in many fields. However, existing algorithms based on visual attention models cannot obtain satisfactory results for SAR image target detection under complex environmental conditions. After analysing the existing visual attention models, we combine the pyramid model of visual attention with singular value decomposition to simulate the human retina, which can make the visual attention model more suitable to the characteristics of SAR images. We introduce variance weighted information entropy into the model to optimize the detection results. The results obtained by the existing visual attention algorithm for target detection in SAR images yield a large number of false alarms and misses. However, the proposed algorithm can improve both the efficiency and accuracy of target detection in a complicated environment and under weak-target conditions. The experimental results validate the performance of our method.

False Alarm Detection in Cyber-physical Systems for Healthcare Applications

Cyber-Physical System (CPS) is an integration of physical processes with computation and communication. CPS connects the virtual world with physical world. It has the ability to add more intelligence to social life. A CPS integrates physical devices, such as sensors and cameras, with cyber (or informational) components to form a situation-integrated analytical system that responds intelligently to dynamic changes in the real-world scenarios. Wireless Sensor Networks (WSN) can be a vital part of CPS as strong sensing capabilities can be one of the major driving factors for CPS applications. Still CPS is considered as a nascent technology and there are many challenges yet to be addressed. These challenges are often posed due to the complexity of communication, computation and the uncertainty of physical processes. CPS can have wide ranging applications, such as smart medical technology, assisted living, environmental control and traffic management. Unfortunately, no unified architecture for CPS has yet been developed, primarily due to variations among the applications. In CPS healthcare application, a wide range of medical sensors are used, however these sensors generate a large number of false alarms. These false alarms add confusion and reduce the efficiency of overall healthcare service. Although a few CPS healthcare architectures have been proposed for healthcare application they all lack of efficient false alarm detection. In this paper, a novel false alarm detection architecture is proposed in CPS for healthcare applications.

Improving intrusion detection for imbalanced network traffic

ABSTRACTThe acceptability and usability of intrusion detection systems get seriously affected with data imbalance in network traffic. A large number of false alarms mean a lot in terms of the acceptability of intrusion detection systems. The reason for the increase in false alerts is that the normal traffic abound. Even with highly accurate intrusion detection systems, the effective detection rate of the minority attack types will be unacceptably low, and those attack types are often the most serious ones. Thus, high accuracy is not necessarily an indicator of high model quality, and therein lays the accuracy paradox of predictive analytics. The cost of missing an attack is higher than the cost of false alarms. The aim of this work is to provide an architecture that enables available intrusion detection systems to work together towards creating a more realistic model of the state of a network. The data‐dependent decision fusion architecture presented in this paper learns from the data and then appropriately gives weighting to the decisions of various intrusion detection systems. The fusion enriches these weighted decisions to provide a single decision, which is better than those of the existing intrusion detection systems. It is also shown that our technique is more flexible and also outperforms other existing fusion techniques such as OR, AND, SVM, and ANN. This method reduces the false positive rate and improves the overall detection rate and, also, the detection rate of minority class types in particular. For illustrative purposes, two different data sets, namely the DARPA 1999 data set as well as the real‐time network traffic embedded with attacks, have been used. Copyright © 2012 John Wiley &amp; Sons, Ltd.

Control Charts for Binary Correlated Variables

To monitor the nonconforming fraction of a production process, usually np or p control charts are used for this purpose. However, in many practical situations, the binary variables are correlated but not easily perceived by practitioners. The aim of this article is to present the maximum likelihood and method of moment estimators of the correlation parameter ρ of an overdispersed binomial distribution. Inferential procedure is also introduced to test the null hypothesis H0: ρ = 0 x H1: ρ &gt; 0. A Shewhart‐type control chart npρ and an Exponentiated Weighted Moving Average (EWMA)‐type control chart (EWMA npρ) are proposed to evaluate the nonconforming fraction when the binary variables are correlated. The traditional np chart is a particular case of the npρ control chart when ρ = 0. The misuse of control limits of np control in case of correlated binary variables will result a large number of false alarms. To have the same performance (in terms of average run length) of the traditional np control chart, the npρ control chart needs at least to double the sample size. Numerical example illustrates the proposal. Copyright © 2012 John Wiley &amp; Sons, Ltd.

Mapping invasive Fallopia japonica by combined spectral, spatial, and temporal analysis of digital orthophotos

Japanese knotweed (Fallopia japonica) is listed among 100 of the World's worst invasive alien species and poses an increasing threat to ecosystems and agriculture in Northern America, Europe, and Oceania. This study proposes a remote sensing method to detect local occurrences of F. japonica from low-cost digital orthophotos taken in early spring and summer by concurrently exploring its temporal, spectral, and spatial characteristics. Temporal characteristics of the species are quantified by a band ratio calculated from the green and red spectral channels of both images. The normalized difference vegetation index was used to capture the high near-infrared (NIR) reflectance of F. japonica in summer while the characteristic texture of F. japonica is quantified by calculating gray level co-occurrence matrix (GLCM) measures. After establishing the optimum kernel size to quantify texture, the different input features (spectral, spatial, and texture) were stacked and used as input to the random forest (RF) classifier. The proposed method was tested for a built-up and semi-natural area in Slovenia.The spectral, spatial, and temporal provided an equally important contribution for differentiating F. japonica from other land cover types. The combination of all signatures resulted in a producer accuracy of 90.3% and a user accuracy of 98.1% for F. japonica when validation was based on independent regions of interest. A producer accuracy of 61.4% was obtained for F. japonica when comparing the classification result with all occurrences of F. japonica identified during a field validation campaign. This is an encouraging result given the very small patches in which the species usually occur and the high degree of intermingling with other plants. All hot spots were identified and even likely infestations of F. japonica that had remained undiscovered during the field campaign were detected. The probability images resulting from the RF classifier can be used to reduce the relatively large number of false alarms and may assist in targeted eradication measures. Classification skill only slightly reduced when NIR information was not considered, which is an important recognition with regard to transferability of the method to the most basic type of digital color orthophotos. The possibility to use orthophotos, which at most municipalities are commonly available and easily accessible, facilitates an immediate implementation of the approach in situations where intervention is urgent.

Minimize the False Positive Rate in a Database Intrusion Detection System

A database intrusion detection system (DIDS) is used to detect potential violations in database security. DIDS follows other traditional database security mechanisms and network security mechanisms such as firewall and network intrusion detection. Therefore, it faces the intrusion from internal users or the intrusion that can be passed through other security layers. This means that the number of intrusion event is rare compared to the number of the normal event. Therefore, it is not efficient to raise a large number of false alarms to achieve a high detection rate. This paper introduces an enhancement for the data dependency model and integrates it with access control to override the high rate of false alarm and increase the detection rate.

Weighted Centroid Modified Simplex and Linear Constrained Response Surface Optimization Methods for the Xbar-R Chart Variable Determination

Problem statement: Although economic Xbar-R chart designs do guarantee the minimal operating cost, they typically have poor levels of statistical performance measures. The obvious limitation of the economic design is that the Type I error rate seems to be very high for many situations and will cause a large number of false alarms. This situation leads to an investigation of appropriate levels of control chart variables which consist of a sample size, an interval between samples or sampling frequency and the control chart limits. Approach: Evolutionary operations via the weighed centroid modified simplex, WCMSM and linear constrained response surface optimization, LCRSOM, methods are applied to optimize the Xbar-R chart variables in the analytical model called as the operating cost function. WCMSM allows the simplex to converge more rapidly towards an optimum via the weighted centroid of the hyperface by expansion and multiple ways of simplex contraction along the line of conventional reflection in order to speed up the convergence. LCRSOM is a combination of the principles of experimental designs, least squares and related mathematical programming models to approach the optimum. Results: The computational results for economic Xbar-R charts via both methods reveal that the process quality level affects the total cost more than relevant errors from selecting and inspecting samples including identifying assignable causes. However, total costs obtained from the LCRSOM seem to be better for all process scenarios. Conclusions: On Xbar-R charts, if a process is at the high quality level the total cost is better than a process with a low quality level without a consideration of errors from selecting/inspecting samples and identifying assignable causes.

Opportunities for Preventing Rear-End Crashes: Findings from the Analysis of Actual Freeway Crash Data

To date most traffic crash analyses have been conducted using aggregated crash data. The main focus was given to determining the relationship between crashes and corresponding variables such as traffic volume, speed, speed variance, and geometry conditions. Few studies have focused on the cause of crashes at the individual vehicular level. Recently, the Minnesota Traffic Observatory at the University of Minnesota developed a set of vehicle trajectory data containing five actual rear-end crashes. This article analyzes these data and attempts to establish a trigger factor for preventing crashes. An inverse of time-to-collision value of 0.4 detected all five actual crashes before the collision, but with a large number of false alarms. An additional trigger factor, the deceleration rate difference between leading and following vehicles greater than 15 ft/sec2, completely eliminated those false alarms. In addition, it was found that an advanced warning intended to alert the driver offers little help in preventing the crashes. This is because a driver reaction time of about 0.57 sec is required before initiating deceleration. Thus, the deceleration rate required to avoid a crash became impractical, resulting in actual avoidance of only 20% crashes. This indicated that an automated braking system should be applied to prevent crashes or effectively mitigate the crash impacts.

Visual inspection of glass bottlenecks by multiple-view analysis

The narrow structure of bottlenecks poses a very challenging problem for automated visual inspection systems and surprisingly, this issue has received little attention in literature. Bottleneck inspection is highly relevant to the fabrication of glass bottles, e.g., for the wine and beer industry. Defects in glass bottles can arise in various situations such as an incomplete reaction in a batch, batch contaminants and interactions of the melted material among others. This paper presents an inspection approach that utilises geometry of multiple views along with a rich set of feature descriptors to discriminate real flaws from false alarms in uncalibrated images of glass bottlenecks. The proposed method is based on an automatic multiple view inspection (AMVI) technique for the automatic detection of flaws. This technique involves an initial step that extracts numerous segmented regions from a set of views of the object under inspection. These regions are subsequently classified either as real flaws or as false alarms. The classification process considers that image noise and false alarms occur as random events in different views while real flaws induce geometric and featural relations in the views where they appear. Therefore, by analysing such relations it is possible to successfully localise real flaws and to discard a large number of false alarms. An important characteristic of the proposed methodology is the complete lack of camera calibration which makes our method very suitable for applications where camera calibration is difficult or expensive to carry out. Our inspection system achieves a true positive rate of 99.1% and a false positive rate of 0.9%.

A Comparison of Dynamical and Statistical Predictions of Weekly Tropical Cyclone Activity in the Southern Hemisphere

Abstract The skill of the European Centre for Medium-Range Weather Forecasts (ECMWF) forecast system to predict the occurrence of tropical cyclones (TCs) over the Southern Hemisphere during weekly periods has been evaluated and compared to the skill of a state-of-the-art statistical model. Probabilistic skill scores have been applied to a common series of hindcasts produced with the dynamical and statistical models. The ECMWF hindcasts have higher relative operating characteristic (ROC) scores than the statistical model for the first three weeks of integrations. The dynamical model also has skill over the Indian Ocean in week 4. The ECMWF hindcasts have lower Brier skill scores than the statistical model after week 2, which is likely because this version of the ECMWF model creates about 30% more TCs than observations and therefore generates a large number of false alarms. A simple calibration has been applied to the ECMWF probabilistic forecasts that significantly improves their reliability, but at the expense of the sharpness. The calibrated dynamical model has higher Brier skill scores than the statistical model during the first three weeks, although the statistical model remains more reliable. The multimodel combination of the calibrated dynamical forecasts with the statistical forecasts helps to improve the reliability of the ECMWF forecasts. The Brier skill score of the multimodel exceeds the Brier skill scores of the individual models, but with less sharpness than the calibrated dynamical model. This result suggests that the statistical model can be useful as a benchmark for dynamical models and as a component of a multimodel combination to improve the skill of the dynamical model. Potential economic value diagrams confirm that the multimodel forecasts are useful up to week 3 over the Southern Hemisphere.

Detecting people in dense crowds

We propose a scheme to detect individuals in any image frame of a video sequence showing densely crowded scenes against cluttered backgrounds. The method uses only spatial information, and in an initial pass through the image a trained Viola–Jones-type local detector is used to locate individuals in the densely crowded scene. This yields a large number of false alarms. Hence, in a second step, we seek to reduce the false alarms, and propose two methods for this. In the first, color information from the initially detected windows is passed to a classifier to reduce the false alarms. This classifier consists of a cascade of boosted classifiers with Haar-like features as input and is trained with color information from local windows. In the second method, a weak perspective model of an uncalibrated camera is used to further reduce the false alarm rate while maintaining the detection rate. This is based on the size and locations of the detections in the image frame, without the use of any 3D world information. Results are presented in the form of receiver operating characteristic curves. For instance, at a 79.0% detection accuracy, the false alarm rate is 20.3%.

Classification of marine mammal vocalizations using an automatic aural classifier.

Passive sonar systems are often used to detect marine mammal vocalizations in order to localize and track them. Unfortunately, transients generated by sources other than marine mammals can also trigger passive sonar systems which leads to a large number of false alarms. Furthermore, even in the case of a successful detection, classifying the genus is often required and this typically requires expertise not readily available on the vessel. Perceptual signal features—similar to those employed in the human auditory system—have been used to reduce false alarms in active sonar by automatically discriminating between target and clutter echoes. This contributes to improved sonar performance [Young and Hines, J. Acoust. Soc. Am. 122, 1502–1517 (2007)]. Many of the features were inspired by research directed at discriminating the timbre of different musical instruments (a passive classification problem) which suggests it might be applied to classify marine mammal vocalizations. To test this hypothesis, the automatic aural classifier was trained and tested on a set of marine mammal vocalizations from a variety of species. This paper will provide an overview of the aural classifier’s architecture, describe the preparation of the data set, including the attempt to provide ground-truth confirmation of the data, and present some preliminary results.

Age‐related changes in the control of episodic retrieval: an ERP study of recognition memory in children and adults

We examined developmental aspects of the ability to monitor the temporal context of an item's previous occurrence while event-related potentials (ERPs) were recorded. In a continuous recognition task, children between 10 and 12 years and young adults watched a stream of pictures repeated with a lag of 10-15 intervening items and indicated recurrences. In a second run, these already familiar pictures were repeated as non-targets along with new pictures, while subjects were instructed to indicate only recurrences within the run. Young adults were able to maintain high performance levels in both tasks, whereas children had longer response times and committed a large number of false alarms to non-targets. ERPs in both age groups showed similar parietal old/new effects for target repetitions within runs. In addition, adults' ERPs showed similar old/new effects at frontal electrodes for repetitions and non-targets, presumably reflecting assessments of familiarity, whereas for children repeated relative to first presentations were associated with more negative-going waveforms at anterior frontal recording sites. Together, these results suggest a continuing maturation of the brain networks assessing novelty or familiarity. Recollection as indexed by parietal old/new effects appeared similar between young adults and children, but the development of controlled episodic retrieval, resulting in recollection of non-target information, appears to continue well into adolescence.