Failure Detection Rates Research Articles

A Report on a Nationwide Surveillance System for Pediatric Acute Hepatitis of Unknown Etiology in Korea.

Several cases of pediatric acute hepatitis of unknown etiology related to adenoviral infections have been reported in Europe since January 2022. The aim of this study was to compare the incidence, severity, possible etiology, and prognosis of the disease with those in the past in Korea. The surveillance group collected data between May and November 2022 using a surveillance system. Acute hepatitis of unknown etiology was defined in patients aged < 16 years with a serum transaminase level > 500 IU/L, not due to hepatitis A-E or other underlying causes. For comparison, data from 18 university hospitals were retrospectively collected as a control group between January 2021 and April 2022. We enrolled 270 patients (mean age, 5 years). The most common symptom was fever. However, the incidence was similar between 2021 and 2022. Liver function test results, number of patients with acute liver failure (ALF), liver transplantation (LT), death, and adenovirus detection rates did not differ between the two groups. None of the adenovirus-positive patients in either group experienced ALF, LT, or death. In the surveillance group, adenovirus-associated virus-2 was detected in four patients, one of whom underwent LT. Patients with an unknown etiology showed significantly higher bilirubin levels, a lower platelet count, and a higher LT rate than patients with a possible etiology. The incidence of pediatric acute hepatitis of unknown etiology and adenovirus detection rate have not increased in Korea.

A Disk Failure Prediction Method Based on Active Semi-supervised Learning

Disk failure has always been a major problem for data centers, leading to data loss. Current disk failure prediction approaches are mostly offline and assume that the disk labels required for training learning models are available and accurate. However, these offline methods are no longer suitable for disk failure prediction tasks in large-scale data centers. Behind this explosive amount of data, most methods do not consider whether it is not easy to get the label values during the training or the obtained label values are not completely accurate. These problems further restrict the development of supervised learning and offline modeling in disk failure prediction. In this article, Active Semi-supervised Learning Disk-failure Prediction ( ASLDP ), a novel disk failure prediction method is proposed, which uses active learning and semi-supervised learning. According to the characteristics of data in the disk lifecycle, ASLDP carries out active learning for those clear labeled samples, which selects valuable samples with the most significant probability uncertainty and eliminates redundancy. For those samples that are unclearly labeled or unlabeled, ASLDP uses semi-supervised learning for pre-labeled by calculating the conditional values of the samples and enhances the generalization ability by active learning. Compared with several state-of-the-art offline and online learning approaches, the results on four realistic datasets from Backblaze and Baidu demonstrate that ASLDP achieves stable failure detection rates of 80–85% with low false alarm rates. In addition, we use a dataset from Alibaba to evaluate the generality of ASLDP . Furthermore, ASLDP can overcome the problem of missing sample labels and data redundancy in large data centers, which are not considered and implemented in all offline learning methods for disk failure prediction to the best of our knowledge. Finally, ASLDP can predict the disk failure 4.9 days in advance with lower overhead and latency.

On Cooperative Fault Management in Multi-Domain Optical Networks Using Hybrid Learning

This paper presents a hybrid learning approach for cooperative fault management in multi-domain optical networks (MD-ONs). The proposed approach relies on a broker-based MD-ON architecture for coordination of inter-domain service provisioning. We first propose a self-supervised learning design for soft failure detection. The self-supervised learning design makes use of a clustering algorithm for extracting normal and abnormal patterns from optical performance monitoring data and a supervised learning-based classifier trained with the learned patterns for online detection. To facilitate high soft failure detection accuracy in the absence of sufficient abnormal data for training, the proposed design estimates model uncertainties during predictions and identifies instances associated with high uncertainties as also soft failures. Then, we extend the self-supervised learning design and present a federated learning framework for the broker plane and DMs to learn cooperatively while complying with the privacy constraints of each domain. Finally, a data-driven soft failure localization scheme that operates by analyzing the patterns of data is proposed as a complement to the existing approaches. Performance evaluations indicate that the self-supervised learning design can achieve soft failure detection accuracy of up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim 97\%$</tex-math></inline-formula> with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$0.01\%-0.04\%$</tex-math></inline-formula> false alarm rate, while federated learning enables DMs to realize <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$&gt;90\%$</tex-math></inline-formula> soft failure detection rates in the cases of highly unbalanced data distribution (two of the three domains possess zero abnormal data for training).

A 12-nm Autonomous Driving Processor With 60.4 TOPS, 13.8 TOPS/W CNN Executed by Task-Separated ASIL D Control

This article proposes an automotive safety integrity level (ASIL) D, which is the highest automotive integrity level specified in ISO 26262, and a target application processor for driving automation systems with a high convolutional neural network (CNN) processing performance of 60.4 trillion operations per second (TOPS) with high power efficiency of 13.8 TOPS/W. To achieve both performance and power efficiency, a stream processing architecture specialized for CNN hardware module is adopted to implement many low-power arithmetic units. In addition, 6 MB of local memories are implemented to reduce data transfers between dynamic random access memory (DRAM) and the CNN hardware, thereby improving the execution efficiency of the arithmetic units and saving power consumption caused by the data transfer. In order to support high safety integrity level with power efficiency, we provide safety mechanisms with high failure detection rates only for the hardware used in applications that require ASIL D support. The configuration of two CNN modules can switch between lockstep and single operation depending on the use case, thus achieving a tradeoff between performance and ASIL while maintaining power efficiency. In addition, the freedom from interference (FFI) concept defined in ISO 26262 is achieved by providing mechanisms to prevent low safety level tasks from interfering with high safety level tasks running concurrently inside the processor.

High-Potential Test for Quality Control of Separator Defects in Battery Cell Production

Lithium-ion batteries are a key technology for electromobility; thus, quality control in cell production is a central aspect for the success of electric vehicles. The detection of defects and poor insulation behavior of the separator is essential for high-quality batteries. Optical quality control methods in cell production are unable to detect small but still relevant defects in the separator layer, e.g., pinholes or particle contaminations. This gap can be closed by executing high-potential testing to analyze the insulation performance of the electrically insulating separator layer in a pouch cell. Here, we present an experimental study to identify different separator defects on dry cell stacks on the basis of electric voltage stress and mechanical pressure. In addition, finite element modeling (FEM) is used to generate physical insights into the partial discharge by examining the defect structures and the corresponding electric fields, including topographical electrode roughness, impurity particles, and voids in the separator. The test results show that hard discharges are associated with significant separator defects. Based on the study, a voltage of 350 to 450 V and a pressure of 0.3 to 0.6 N/mm2 are identified as optimum ranges for the test methodology, resulting in failure detection rates of up to 85%.

Failure Detection in Eucalyptus Plantation Based on UAV Images

The information of the locations and numbers of failures is crucial to precise management of new afforestation, especially during seedling replanting in young forests. In practice, foresters are more accustomed to determining the locations of failures according to their rows than based on their geographical coordinates. The relative locations of failures are more difficult to collect than the absolute geographic coordinates which are available from an orthoimage. This paper develops a novel methodology for obtaining the relative locations of failures in rows and counting the number of failures in each row. The methodology contains two parts: (1) the interpretation of the direction angle of seedlings rows on an unmanned aerial vehicle (UAV) orthoimage based on the probability statistical theory (called the grid-variance (GV) method); (2) the recognition of the centerline of each seedling rows using K-means and the approach to counting failures in each row based on the distribution of canopy pixels near the centerline of each seedling row (called the centerline (CL) method). The experimental results showed that the GV method can accurately interpret the direction angle of rows (45°) in an orthoimage and the CL method can quickly and accurately obtain the numbers and relative locations of failures in rows. The failure detection rates in the two experimental areas were 91.8% and 95%, respectively. These research findings can provide technical support for the precise cultivation of planted seedling forests.

Comparison of postal and non-postal post-vasectomy semen sample submission strategies on compliance and failures: an 11-year analysis of the audit database of the Association of Surgeons in Primary Care of the UK

BackgroundVasectomy occlusive success is defined by the recommendation of ‘clearance’ to stop other contraception, and is elicited by post-vasectomy semen analysis (PVSA). We evaluated how the choice of either a...

Machine Learning Algorithms for Automatic Anomalies Detection in Data Storage Systems Operation

Data storage reliability and availability play important role for a wide range of services and business processes. Manufacturers provide data storage systems that resistant to hardware and software failures but not for all cases. Well-timed detection of these failures help to recover the system faster and prevent the failures before they occur. In this work a range of machine learning and time series analysis algorithms for failures detection is considered. The algorithms are applied and compared on the real data storage system. Preliminary results show that binary classification methods demonstrate high failure detection and low false alarm rates. Time series prediction based approach shows similar results and outperforms one-class classification methods.

Multiobjective Optimization Approach for Robust Bridge Damage Identification against Sensor Noise

One of the important goals of structural health monitoring is to identify structural damage using measured responses. However, such damage identification is sensitive to noises in the response measurements. Even a small change in the measurement may result in a significantly biased damage assessment. The goal of this paper is to expand the multiobjective optimization approach developed for robust damage identification in order to facilitate its applications to more realistic bridge damage identification problems. Specifically, a benchmark problem on highway bridges, developed under the auspices of International Association for Bridge Maintenance and Safety (IABMAS), is investigated. Various issues regarding sensor noises, multiple measurements, and loading scenarios are addressed to improve the robustness of bridge damage identification. A major finding from this study is that the stochastic process of Pareto optimal solutions obtained in a single run not only captures the actual damage locations successfully but also provides useful information such as damage‐detected ratio on the potential candidates for damage to be inspected on site. Moreover, it is shown through the success, failure, and partial detection rates that the robustness of the proposed approach can be improved by using appropriate excitation scenarios and multiple sets of measurement data.

Hard drive failure prediction using Decision Trees

This paper proposes two hard drive failure prediction models based on Decision Trees (DTs) and Gradient Boosted Regression Trees (GBRTs) which perform well in prediction performance as well as stability and interpretability. The models are evaluated on a real-world dataset containing 121,698 drives in total. Experimental results show the DT model predicts over 93% of failures at a false alarm rate under 0.01%, and the GBRT model can achieve about 90% failure detection rate without any false alarms. Moreover, the GBRT model evaluates drive health (or fault probability) which provides a quantitative indicator of failure urgency. This enables operators to allocate system resources accordingly for pre-warning migrations while maintaining the quality of user services.Aiming at practical application of prediction models, we test the models on another real-world dataset with different drive models, on a real-world hybrid dataset with multiple drive models, and on several datasets containing fewer drives. Both prediction models show steady prediction performance, with high failure detection rates (80% to 96%) and low false alarm rates (0.006% to 0.31%). We also implement a reliability model for RAID-6 systems with proactive fault tolerance and show that the proposed models can significantly improve the reliability and/or reduce construction and maintenance cost of large-scale storage systems.

Detecting Node Failures in Mobile Wireless Networks: A Probabilistic Approach

Detecting node failures in mobile wireless networks is very challenging because the network topology can be highly dynamic, the network may not be always connected, and the resources are limited. In this paper, we take a probabilistic approach and propose two node failure detection schemes that systematically combine localized monitoring, location estimation and node collaboration. Extensive simulation results in both connected and disconnected networks demonstrate that our schemes achieve high failure detection rates (close to an upper bound) and low false positive rates, and incur low communication overhead. Compared to approaches that use centralized monitoring, our approach has up to 80 percent lower communication overhead, and only slightly lower detection rates and slightly higher false positive rates. In addition, our approach has the advantage that it is applicable to both connected and disconnected networks while centralized monitoring is only applicable to connected networks. Compared to other approaches that use localized monitoring, our approach has similar failure detection rates, up to 57 percent lower communication overhead and much lower false positive rates (e.g., 0.01 versus 0.27 in some settings).

Testing and Validation of a Psychophysically Defined Metric of Display Clutter

Combinations of cockpit display features may lead to increased pilot perceptions of clutter. This research sought to capture pilot perceptions of display clutter associated with primary flight display features during a vertical takeoff and landing scenario and to validate a multidimensional measure of clutter previously developed for a fixed-wing environment. Sixteen active fixed-wing pilots were recruited for the study that used a simulator configured as a vertical takeoff and landing aircraft. A factor analysis was used to reduce the number of subdimensions of the clutter measure based on previous ratings data. The simplified measure revealed an increase in the number of active display features to cause an increase in perceived clutter. Displays including synthetic vision system features were perceived as significantly more cluttered than those without. Although a tunnel (highway in the sky) feature also contributed to clutter, pilots achieved higher navigation system failure detection rates when the feature was active. Significant positive correlations were found between perceived clutter and visual display properties but not between perceived clutter and performance. Although pilots rated some displays as being highly cluttered, the increased information aided navigation failure detection. Overall, the clutter measure was found to have validity and sensitivity for application across diverse flight domains.

Intraoperative coronary graft assessment

Intraoperative graft assessment in coronary artery bypass grafting is infrequently performed. Nevertheless, studies show an immediate graft closure rate of 5-9% and a 1-year closure rate of 20-30%. Coronary angiography is the 'gold standard' for graft assessment yet has been seldom employed because of logistical problems and image quality. Two methods, transit time flow measurement and intraoperative fluorescence imaging are simple, safe, and expeditious. Intraoperative graft failure detection rates of 2-5% have been reported. Early graft occlusion occurs frequently after coronary artery bypass grafting. Two relatively simple but underutilized methods of intraoperative graft assessment have been shown to be predictive of graft failure. Wider use of these techniques as well as wider availability of hybrid operating rooms, which will allow intraoperative coronary angiography, may reduce graft failure.

Anticipating Risk for Human Subjects Participating in Clinical Research: Application of Failure Mode and Effects Analysis

Failure Mode and Effects Analysis (FMEA) is a method applied in various industries to anticipate and mitigate risk. This methodology can be more systematically applied to the protection of human subjects in research. The purpose of FMEA is simple: prevent problems before they occur. By applying FMEA process analysis to the elements of a specific research protocol, the failure severity, occurrence, and detection rates can be estimated for calculation of a “risk priority number" (RPN). Methods can then be identified to reduce the RPN to levels where the risk/benefit ratio favors human subject benefit, to a greater magnitude than existed in the pre-analysis risk profile. At the very least, the approach provides a checklist of issues that can be individualized for specific research protocols or human subject populations.