scholarly journals Outlier Detection in Growth Data: Beyond Biologically Implausible Values

2020 ◽  
Vol 4 (Supplement_2) ◽  
pp. 1174-1174
Author(s):  
Paraskevi Massara ◽  
Robert Bandsma ◽  
Celine Bourdon ◽  
Jonathon Maguire ◽  
Elena Comelli ◽  
...  
Keyword(s):  
Outlier Detection ◽  
Sensitivity And Specificity ◽  
Detection Method ◽  
Nutritional Assessment ◽  
Empirical Method ◽  
Child Growth ◽  
Detection Methods ◽  
Healthy Children ◽  
Growth Data ◽  
Growth Standards

Abstract Objectives Eliminating anthropometry measurement error and employing outlier and biological implausible values (BIV) detection methods adapted to longitudinal measurements is important for the study of growth. This work aimed to review and assess the accuracy of the available BIV and outlier detection methods and propose a growth trajectory outlier detection method. Methods We included 2354 infants from the Applied Research Group for Kids (TARGet Kids! ) cohort-based in Toronto (ON, Canada) that recruits healthy children from birth to 5 years of age. We considered infants with at least 8 length and weight measurements available between the 1st and the 24th month of age. Weight-for-length z-scores (wflz) were calculated using the WHO growth standards. Outlier measurements were randomly introduced in 5% of the wflz measurements using a normal distribution (μ = 0, σ = 1). We employed 4 outlier detection methods; an empirical detection method for BIV using the cut-offs derived from the WHO Child Growth Standards, a clustering method, a method based on cluster prototypes for individual outlier measurements and a method based on cluster prototypes for entire growth trajectories. Each method was applied individually and evaluated using the sensitivity and specificity indexes based on the manually introduced outliers. We also calculated the Kappa statistic to evaluate the agreement of each method against the manual outliers. Results After excluding premature (<37 weeks), low birth weight (<1500 g) neonates and children with missing length and weight measurements, we analyzed 393 children with a total of 3144 measurements. Sensitivity and specificity for the four methods ranged between 4.4%–55.0% and 83.7% −99.7%, respectively, with kappa being non-significant (P > 0.05) only for the empirical. The clustering detection method reported a higher finding rate, while the empirical method found most of the BIV, but few of the rest of the outliers. Conclusions BIV account for a small portion of the possible outliers in growth datasets. We show that additional statistical or model-based methods are required for a more comprehensive outlier detection process, which has implications for growth analysis and nutritional assessment. Funding Sources Joannah and Brian Lawson Center for Child Nutrition, Connaught Fund, Onassis Foundation.

scholarly journals A Review on Outliers-Detection Methods for Multivariate Data

2021 ◽  
Vol 3 (1) ◽  
pp. 1-15
Author(s):  
Sharifah Sakinah Syed Abd Mutalib ◽  
Siti Zanariah Satari ◽  
Wan Nur Syahidah Wan Yusoff
Keyword(s):  
Cluster Analysis ◽  
Multivariate Analysis ◽  
Outlier Detection ◽  
High Dimension ◽  
Detection Method ◽  
Multivariate Data ◽  
Projection Pursuit ◽  
Detection Methods ◽  
And Cluster Analysis ◽  
Detection Of Outliers

Data in practice are often of high dimension and multivariate in nature. Detection of outliers has been one of the problems in multivariate analysis. Detecting outliers in multivariate data is difficult and it is not sufficient by using only graphical inspection. In this paper, a nontechnical and brief outlier detection method for multivariate data which are projection pursuit method, methods based on robust distance and cluster analysis are reviewed. The strengths and weaknesses of each method are briefly discussed.

scholarly journals Outlier Detection Method for Flash Flood Disaster Monitoring Data based on Information Entropy

2021 ◽  
Vol 2138 (1) ◽  
pp. 012013
Author(s):  
Yongzhi Chen ◽  
Ziao Xu ◽  
Chaoqun Niu
Keyword(s):  
Outlier Detection ◽  
Information Entropy ◽  
Detection Method ◽  
Flash Flood ◽  
False Positive Rate ◽  
Flood Disaster ◽  
Detection Methods ◽  
Positive Rate ◽  
Disaster Monitoring ◽  
Local Outlier

Abstract In the research of flash flood disaster monitoring and early warning, the Internet of Things is widely used in real-time information collection. There are abnormal situations such as noise, repetition and errors in a large amount of data collected by sensors, which will lead to false alarm, lower prediction accuracy and other problems. Aiming at the characteristic that outliers flow of sensors will cause obvious fluctuation of information entropy, this paper proposes a local outlier detection method based on information entropy and optimized by sliding window and LOF (Local Outlier Factor). This method can be used to improve the data quality, thus improving the accuracy of disaster prediction. The method is applied to data stream processing of water sensor, and the experimental results show that the method can accurately detect outliers. Compared with the existing detection methods that only use data distance to determine, the test positive rate is improved and the false positive rate is reduced.

scholarly journals Anomaly Pattern Detection in Streaming Data Based on the Transformation to Multiple Binary-Valued Data Streams

2021 ◽  
Vol 12 (1) ◽  
pp. 19-27
Author(s):  
Taegong Kim ◽  
Cheong Hee Park
Keyword(s):  
Outlier Detection ◽  
Data Streams ◽  
Data Stream ◽  
Detection Method ◽  
Binary Classification ◽  
Streaming Data ◽  
Pattern Detection ◽  
Detection Methods ◽  
Anomaly Pattern ◽  
Isolation Forest

Abstract Anomaly pattern detection in a data stream aims to detect a time point where outliers begin to occur abnormally. Recently, a method for anomaly pattern detection has been proposed based on binary classification for outliers and statistical tests in the data stream of binary labels of normal or an outlier. It showed that an anomaly pattern can be detected accurately even when outlier detection performance is relatively low. However, since the anomaly pattern detection method is based on the binary classification for outliers, most well-known outlier detection methods, with the output of real-valued outlier scores, can not be used directly. In this paper, we propose an anomaly pattern detection method in a data stream using the transformation to multiple binary-valued data streams from real-valued outlier scores. By using three outlier detection methods, Isolation Forest(IF), Autoencoder-based outlier detection, and Local outlier factor(LOF), the proposed anomaly pattern detection method is tested using artificial and real data sets. The experimental results show that anomaly pattern detection using Isolation Forest gives the best performance.

scholarly journals Identification of Spikes in Time Series

2019 ◽  
Vol 8 (1) ◽  
Author(s):  
Dana E. Goin ◽  
Jennifer Ahern
Keyword(s):  
Time Series ◽  
Sensitivity And Specificity ◽  
Kalman Filtering ◽  
Detection Method ◽  
Detection Methods ◽  
Spike Detection ◽  
Overall Performance ◽  
The Mean ◽  
Arima Modeling ◽  
Smoothing Procedure

Abstract Researchers interested in the effects of exposure spikes on an outcome need tools to identify unexpectedly high values in a time series. However, the best method to identify spikes in time series is not known. This paper aims to fill this gap by testing the performance of several spike detection methods in a simulation setting. We created simulations parameterized by monthly violence rates in nine California cities that represented different series features, and randomly inserted spikes into the series. We then compared the ability to detect spikes of the following methods: ARIMA modeling, Kalman filtering and smoothing, wavelet modeling with soft thresholding, and an iterative outlier detection method. We varied the magnitude of spikes from 10 to 50 % of the mean rate over the study period and varied the number of spikes inserted from 1 to 10. We assessed performance of each method using sensitivity and specificity. The Kalman filtering and smoothing procedure had the best overall performance. We applied each method to the monthly violence rates in nine California cities and identified spikes in the rate over the 2005–2012 period.

scholarly journals Diagnostic Accuracy of HPV Detection in Patients with Oropharyngeal Squamous Cell Carcinomas: A Systematic Review and Meta-Analysis

Viruses ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 1692
Author(s):  
Kathrine Kronberg Jakobsen ◽  
Amanda-Louise Fenger Carlander ◽  
Simone Kloch Bendtsen ◽  
Martin Garset-Zamani ◽  
Charlotte Duch Lynggaard ◽  
...  
Keyword(s):  
Diagnostic Accuracy ◽  
Sensitivity And Specificity ◽  
Detection Method ◽  
Meta Analysis ◽  
Squamous Cell Carcinomas ◽  
Tumour Tissue ◽  
Detection Methods ◽  
Cochrane Library ◽  
Blood Samples ◽  
The Cochrane Library

The aim of the study was to evaluate the diagnostic accuracy of Human Papillomavirus (HPV) techniques in oropharyngeal cancer. PubMed, EMBASE, the Cochrane Library and clinicaltrials.org were systematically searched for studies reporting methods of HPV detection. Primary outcomes were sensitivity and specificity of HPV detection. In this case, 27 studies were included (n = 5488, 41.6% HPV+). In this case, 13 studies evaluated HPV detection in tumour tissue, nine studies examined HPV detection in blood samples and five studies evaluated HPV detection in oral samples. Accuracy of HPV detection in tumour tissue was high for all detection methods, with pooled sensitivity ranging from 81.1% (95% CI 71.9–87.8) to 93.1% (95% CI 87.4–96.4) and specificity ranging from 81.1% (95% CI 71.9–87.8) to 94.9% (95% CI 79.1–98.9) depending on detection methods. Overall accuracy of HPV detection in blood samples revealed a sensitivity of 81.4% (95% CI 62.9–91.9) and a specificity of 94.8% (95% CI 91.4–96.9). In oral samples pooled sensitivity and specificity were lower (77.0% (95% CI 68.8–83.6) and 74.0% (95% CI 58.0–85.4)). In conclusion, we found an overall high accuracy for HPV detection in tumour tissue regardless of the HPV detection method used. HPV detection in blood samples may provide a promising new way of HPV detection.

scholarly journals Data Streams Oriented Outlier Detection Method: A Fast Minimal Infrequent Pattern Mining

2021 ◽  
Author(s):  
ZhongYu Zhou ◽  
DeChang Pi
Keyword(s):  
Outlier Detection ◽  
Data Streams ◽  
Pattern Mining ◽  
Detection Method ◽  
Detection Algorithm ◽  
Detection Methods ◽  
Mining Method ◽  
Telemetry Data ◽  
Process Data ◽  
Mining Data Streams

Outlier detection is a common method for analyzing data streams. In the existing outlier detection methods, most of methods compute distance of points to solve certain specific outlier detection problems. However, these methods are computationally expensive and cannot process data streams quickly. The outlier detection method based on pattern mining resolves the aforementioned issues, but the existing methods are inefficient and cannot meet requirements of quickly mining data streams. In order to improve the efficiency of the method, a new outlier detection method is proposed in this paper. First, a fast minimal infrequent pattern mining method is proposed to mine the minimal infrequent pattern from data streams. Second, an efficient outlier detection algorithm based on minimal infrequent pattern is proposed for detecting the outliers in the data streams by mining minimal infrequent pattern. The algorithm proposed in this paper is demonstrated by real telemetry data of a satellite in orbit. The experimental results show that the proposed method not only can be applied to satellite outlier detection, but also is superior to the existing methods.

scholarly journals Prevalence of Chronic Otitis Media among Undernourished Children

2020 ◽  
Vol 10 (01) ◽  
pp. 27-30
Author(s):  
Shehanaaz Shajahan ◽  
Rajeshwary Aroor
Keyword(s):  
Otitis Media ◽  
Nutritional Assessment ◽  
Chronic Otitis Media ◽  
Child Growth ◽  
World Health ◽  
Normal Children ◽  
Suppurative Otitis Media ◽  
Growth Standards ◽  
Group A ◽  
Group B

Abstract Objective This study aimed to identify the role of nutrition in the etiology of chronic suppurative otitis media (CSOM) by comparing the prevalence of CSOM between undernourished children with normal children aged between 10 and 12 years. Materials and Methods A total of 200 children aged between 10 and 12 years studying in government schools were selected for the study. All the children underwent a general and detailed ENT examination in addition to nutritional assessment based on body mass index calculation, using World Health Organization (WHO) Child Growth Standards Chart. The children were divided into two groups: Group A and Group B. Group A consisted of 100 children who were malnourished and Group B consisted of 100 children who were normal. The presence of CSOM in the two groups was noted. Results and Observations Of the total 200 children, 112 were boys (56%) and 88 were girls (44%). Of the 112 boys, 22 (19.64%) had CSOM and out of 88 girls, 24 (27.27%) had CSOM. Of the total 46 children found to have CSOM, 35 children (76.1%) belonged to Group A and 11 children (23.9%) belonged to Group B. Conclusion Our study shows that there is a higher prevalence of CSOM among undernourished children than in normal children. High prevalence of CSOM in undernourished children is a preventable health problem that needs health education and active intervention.

scholarly journals Poor Head Growth Is Associated with Later Mental Delay among Vietnamese Preterm Infants: A Follow-up Study

2020 ◽  
Author(s):  
Chuong Huu Thieu Do ◽  
Malene Landbo Børresen ◽  
Freddy Karup Pedersen ◽  
Tinh Thu Nguyen ◽  
Hung Thanh Nguyen ◽  
...  
Keyword(s):  
Preterm Infants ◽  
Child Growth ◽  
Physical Growth ◽  
World Health ◽  
Growth Data ◽  
Growth Standards ◽  
Head Growth ◽  
Who Standards ◽  
Catch Up

Abstract Background Preterm infants in low- and middle-income countries are at high risk of poor physical growth, but their growth data are still scarce. Objectives To describe the growth of Vietnamese preterm infants in the first 2 years, and to compare with references: World Health Organization (WHO) child growth standards, and healthy Southeast Asian (SEA) infants. Further, to assess the association between growth in the first year and neurodevelopment at 2 years corrected age (CA). Methods We conducted a cohort study to follow up preterm infants discharged from a neonatal intensive care unit for 2 years. Weight, length and head circumference (HC) were measured at 3, 12 and 24 months CA. Neurodevelopment was assessed using Bayley Scales of Infant and Toddler Development—3rd Edition at 24 months CA. Results Over 90% of the cohort showed catch-up weight at 3 months CA. Weight and length were comparable to healthy SEA but were lower than WHO standards. HC was significantly smaller than those of WHO standards with HC Z-scores steadily decreasing from −0.95 at 3 months CA to −1.50 at 24 months CA. Each one decrement of HC Z-score from 3 to 12 months CA was associated with nearly twice an increase in odds of mental delay at 24 months CA (odds ratio 1.89; 95% confidence interval 1.02–3.50). Conclusion Vietnamese preterm infants exhibited early catch-up weight but poor head growth, which was associated with later delays in mental development. Our findings support the importance of HC measures in follow-up for preterm infants.

scholarly journals Multi-Level Clustering-Based Outlier’s Detection (MCOD) Using Self-Organizing Maps

2020 ◽  
Vol 4 (4) ◽  
pp. 24
Author(s):  
Menglu Li ◽  
Rasha Kashef ◽  
Ahmed Ibrahim
Keyword(s):  
Outlier Detection ◽  
Detection Method ◽  
Detection Algorithm ◽  
Detection Methods ◽  
Self Organizing Maps ◽  
Business Outcomes ◽  
Online Transactions ◽  
Business Applications ◽  
Efficient Detection ◽  
Multi Level

Outlier detection is critical in many business applications, as it recognizes unusual behaviours to prevent losses and optimize revenue. For example, illegitimate online transactions can be detected based on its pattern with outlier detection. The performance of existing outlier detection methods is limited by the pattern/behaviour of the dataset; these methods may not perform well without prior knowledge of the dataset. This paper proposes a multi-level outlier detection algorithm (MCOD) that uses multi-level unsupervised learning to cluster the data and discover outliers. The proposed detection method is tested on datasets in different fields with different sizes and dimensions. Experimental analysis has shown that the proposed MCOD algorithm has the ability to improving the outlier detection rate, as compared to the traditional anomaly detection methods. Enterprises and organizations can adopt the proposed MCOD algorithm to ensure a sustainable and efficient detection of frauds/outliers to increase profitability (and/or) to enhance business outcomes.

scholarly journals Comparison of sCIM and Other Phenotypic Detection Methods for Carbapenemase-Producing Enterobacterales

2021 ◽  
Author(s):  
Takuya Hosoda ◽  
Yohei Doi ◽  
Masahiro Suzuki
Keyword(s):  
Sensitivity And Specificity ◽  
Detection Method ◽  
Clinical Laboratory ◽  
Detection Methods ◽  
Identification Methods ◽  
Hands On

Simple identification methods for carbapenemase-producing Enterobacterales are required for the clinical laboratory. The simplified carbapenem inactivation method (sCIM) is a carbapenemase detection method that can be performed with less hands-on time than mCIM, but its sensitivity and specificity were suboptimal compared with other phenotypic detection methods when tested against a collection of IMP-producing CPE.

Sign in / Sign up

Export Citation Format

Share Document