Objective. Flares in rheumatoid arthritis (RA) and axial spondyloarthritis (SpA) may influence physical activity. The aim of this study was to assess longitudinally the association between patient-reported flares and activitytracker-provided steps per minute, using machine learning.Methods. This prospective observational study (ActConnect) included patients with definite RA or axial SpA. For a 3-month time period, physical activity was assessed continuously by number of steps/minute, using a consumer grade activity tracker, and flares were self-assessed weekly. Machine-learning techniques were applied to the data set. After intrapatient normalization of the physical activity data, multiclass Bayesian methods were used to calculate sensitivities, specificities, and predictive values of the machine-generated models of physical activity in order to predict patient-reported flares.Results. Overall, 155 patients (1,339 weekly flare assessments and 224,952 hours of physical activity assessments) were analyzed. The mean ± SD age for patients with RA (n = 82) was 48.9 ± 12.6 years and was 41.2 ± 10.3 years for those with axial SpA (n = 73). The mean ± SD disease duration was 10.5 ± 8.8 years for patients with RA and 10.8 ± 9.1 years for those with axial SpA. Fourteen patients with RA (17.1%) and 41 patients with axial SpA (56.2%) were male. Disease was well-controlled (Disease Activity Score in 28 joints mean ± SD 2.2 ± 1.2; Bath Ankylosing Spondylitis Disease Activity Index score mean ± SD 3.1 ± 2.0), but flares were frequent (22.7% of all weekly assessments). The model generated by machine learning performed well against patient-reported flares (mean sensitivity 96% [95% confidence interval (95% CI) 94-97%], mean specificity 97% [95% CI 96-97%], mean positive predictive value 91% [95% CI 88-96%], and negative predictive value 99% [95% CI 98-100%]). Sensitivity analyses were confirmatory.Conclusion. Although these pilot findings will have to be confirmed, the correct detection of flares by machinelearning processing of activity tracker data provides a framework for future studies of remote-control monitoring of disease activity, with great precision and minimal patient burden.
The automatic supervision of IT systems is a current challenge at Orange. Given the size and complexity reached by its IT operations, the number of sensors needed to obtain measurements over time, used to infer normal and abnormal behaviors, has increased dramatically making traditional expert-based supervision methods slow or prone to errors. In this paper, we propose a fast and stable method called UnSupervised Anomaly Detection for multivariate time series (USAD) based on adversely trained autoencoders. Its autoencoder architecture makes it capable of learning in an unsupervised way. The use of adversarial training and its architecture allows it to isolate anomalies while providing fast training. We study the properties of our methods through experiments on five public datasets, thus demonstrating its robustness, training speed and high anomaly detection performance. Through a feasibility study using Orange's proprietary data we have been able to validate Orange's requirements on scalability, stability, robustness, training speed and high performance.
This paper concerns the supervised generative non parametric autoencoder. Classical methods are based on variational non supervised autoencoders (VAE). Variational autoencoders encourage the latent space to fit a prior distribution, like a Gaussian. However, they tend to draw stronger assumptions for the data, often leading to higher asymptotic bias when the model is wrong.
Deep neural networks (DNN) have been applied recently to different domains and perform better than classical state-of-the-art methods. However the high level of performances of DNNs is most often obtained with networks containing millions of parameters and for which training requires substantial computational power. To deal with this computational issue proximal regularization methods have been proposed in the literature but they are time consuming. In this paper, we propose instead a constrained approach. We provide the general framework for this new projection gradient method. Our algorithm iterates a gradient step and a projection on convex constraints. We studied algorithms for different constraints: the classical 1 unstructured constraint and structured constraints such as the 2,1 constraint (Group LASSO). We propose a new 1,1 structured constraint for which we provide a new projection algorithm. Finally, we used the recent "Lottery optimizer" replacing the threshold by our 1,1 projection. We demonstrate the effectiveness of this method with three popular datasets (MNIST, Fashion MNIST and CIFAR). Experiments with these datasets show that our projection method using this new 1,1 structured constraint provides the best decrease in memory and computational power.
Anomaly detection and characterization is a main topic for network managers. Although qualityof-service (QoS) indicators can help to infer problem occurrence, they do not provide immediate insight on the user's perceived quality. Evolved service-level agreements (SLA) will likely be established in terms of quality of experience (QoE) indicators. QoS metrics composing the QoE indicators need to be monitored on a real-time basis by the SLA management tools in order to detect anomalies driving to contract violations. Monitoring SLA contracts may involve the surveillance of individual application sessions for several users. In this work, we address the problem of anomaly detection with impact on a relatively large number of users, either on one or on several types of applications simultaneously. We propose a method to characterize the state of the network, representing QoE indicators as time series and reducing the dimension of the data set. The singular spectrum analysis (SSA) method, using a combination of geometric and statistical methods, is proposed as an analysis tool in order to detect anomalies on QoE indicator evolution.
Abstract-Brief episodes of network faults and performance issues adversely affect the user Quality of Experience (QoE). Besides damaging the current opinions of users, these events may also shape user's future perception of the service. Therefore, it is important to quantify the impact of such events on QoE over time. In this paper, we present our findings on the temporal aspects of user feedback to disturbances on networks. These findings are based on subjective user tests performed in the context of web browsing on an e-commerce website. The results of this study suggest that the QoE drops significantly every time the page load time grows. The after-effects of network disturbances on user QoE remain visible even when the network problems are over, i.e., users do not immediately return to the same level of opinion scores as compared to the corresponding pre-disturbance phase. They tend to remember their recent experiences. Our results also show that there are four segments of users that exist with regards to their feedback to page load times. Network operators may customize their services according to each segment of users to raise the overall QoE. Finally, we show that the exponential relationship provides best fits of QoE and page load times for all segments of users.
Appearance of a curvilinear interface in the ascending aorta which simulates an aortic dissection has been reported when using short-scan-time acquisitions (1 s) and not when using ultrafast CT (50 ms scan time) [1][2][3][4][5][6]. The artifact has been observed on both conventional and spiral scans. This artifact is thought to be related to the motion of the aortic wall in the interval time from end diastole to end systole [1, 5, 6]. Recently, it has been suggested that segmented images from data which have been collected during 0.6 s of a full 1-s scan of a conventional axial image can be retrospectively reconstructed to eliminate this artifact [1]. Spiral CT, which has gained widespread acceptance, requires interpolation to synthesize transaxial images from the volume data set [7]. The simplest approach is linear interpolation between spiral projection data sets from adjacent turns (i. e. 360°apart). However, using this interpolation volume, averaging artifacts due to the broadening of the section sensitivity profile have been noted [8, 9]. Consequently, all current spiral CT scanners reorder the projection data and perform interpolation from views separated by 180°(180°linear interpolation) [9]. In our previous personal experience (unpublished data), we often observed motion artifacts in the proximal part of the ascending aorta which simulate aortic dissection, using a 360°linear interpolation algorithm, as well as other series [3,4]. In several cases these artifacts disappeared when a 180°linear interpolation algorithm was used (Fig. 1).The goal of this study was to evaluate the prevalence of the pseudo-aortic dissection using a 180°linear interpolation algorithm. To our knowledge, the prevalence of the pseudo-aortic dissection using a 180°linear interpolation algorithm, in a large series, has not been reported. Materials and methodsA total of 100 consecutive dynamic contrast-enhanced spiral chest CT examinations, taken during a 1-month interval, performed on a Somatom Plus S CT scanner (Siemens Medical Systems, Erlangen, Germany) for a variety of non-selected indications, excluding clinical suspicion of aortic dissection (i. e. lymphoma followup, lung-cancer staging, mediastinal lymph nodes), were obtained for assessment of the thoracic aorta. The patients included 41 women and 59 men, 19-85 years old (mean age 57 years). Spiral chest CT examinations were performed during a single breath-hold using 10 mm/s table motion, 10 mm collimation, and 10 mm contiguous reconstructions from the lung apex to the diaphragm. The contrast enhancement was provided by a monophasic bolus IV infusion of 120-150 ml of contrast material injected at a rate of 2 ml/s via an antecubital vein. Scanning began 30 s after the initialization of the bolus. Contiguous reconstruction were obtained with a 180°linear interpolation algorithm.The CT examinations were independently and retrospectively reviewed by two experienced radiologists in vascular radiology (P. L. and F. G.). Studies were interpreted as positive if at least one image sho...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.