Filters








831 Hits in 3.7 sec

Unsupervised anomaly detection for discrete sequence healthcare data [article]

Victoria Snorovikhina, Alexey Zaytsev
2020 arXiv   pre-print
The models provide state-of-the-art results for unsupervised anomaly detection for fraud detection in healthcare. Our EDF approach further improves the quality of LSTM model.  ...  We use real data on sequences of patients' visits data from Allianz company for the validation.  ...  Acknowledgments We thank Martin Spindler for providing the data and Ivan Fursov for providing code for data processing.  ... 
arXiv:2007.10098v2 fatcat:zfstsmb5yjdjlhqwdcmasowaoq

Anomaly detection techniques for streaming data–An overview

Saranya Kunasekaran, Chellammal Suriyanarayanan
2020 Malaya Journal of Matematik  
Detecting anomaly in right time facilitates the appropriate control actions for the anomaly in right time. There are several techniques for detecting anomaly.  ...  In this paper, an overview of different techniques for detection of anomaly is presented.  ...  Online eSNN Unsupervised Anomaly Detection (Oe SNN-UAD) OeSNN-UAD is mainly used in univariate time series data for online unsupervised anomaly detection [29] .  ... 
doi:10.26637/mjm0s20/0133 fatcat:blyjw2z4q5datacu7y4lavwchq

DeepFIB: Self-Imputation for Time Series Anomaly Detection [article]

Minhao Liu, Zhijian Xu, Qiang Xu
2021 arXiv   pre-print
Time series (TS) anomaly detection (AD) plays an essential role in various applications, e.g., fraud detection in finance and healthcare monitoring.  ...  Due to the inherently unpredictable and highly varied nature of anomalies and the lack of anomaly labels in historical data, the AD problem is typically formulated as an unsupervised learning problem.  ...  A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data. AAAI, abs/1811.08055, 2019. R. Zhang, P. Isola, and A.A. Efros.  ... 
arXiv:2112.06247v1 fatcat:k7gmfcsnajafdp5qgwq4iuq4f4

Anomalous Example Detection in Deep Learning: A Survey

Saikiran Bulusu, Bhavya Kailkhura, Bo Li, Pramod K. Varshney, Dawn Song
2020 IEEE Access  
This survey tries to provide a structured and comprehensive overview of the research on anomaly detection for DL based applications.  ...  To make DL more robust, several posthoc (or runtime) anomaly detection techniques to detect (and discard) these anomalous samples have been proposed in the recent past.  ...  The metric data anomaly detection techniques consider the use of metrics like distance, correlation, and distribution. The evolving data include discrete sequences and time series.  ... 
doi:10.1109/access.2020.3010274 fatcat:3xjpfc64nvcbtfpwtwwbitjuvm

Anomalous Example Detection in Deep Learning: A Survey [article]

Saikiran Bulusu, Bhavya Kailkhura, Bo Li, Pramod K. Varshney, Dawn Song
2021 arXiv   pre-print
This survey tries to provide a structured and comprehensive overview of the research on anomaly detection for DL based applications.  ...  To make DL more robust, several posthoc (or runtime) anomaly detection techniques to detect (and discard) these anomalous samples have been proposed in the recent past.  ...  The metric data anomaly detection techniques consider the use of metrics like distance, correlation, and distribution. The evolving data include discrete sequences and time series.  ... 
arXiv:2003.06979v2 fatcat:4mogo75b4rbxrc6vph2xmllkue

Anomaly Detection [chapter]

Varun Chandola, Arindam Banerjee, Vipin Kumar
2016 Encyclopedia of Machine Learning and Data Mining  
Identifying such anomalies from observed data, or the task of anomaly detection, is an important and often critical analysis task.  ...  for one domain would perform in another.  ...  ACM Comput Surv 41(3):15:1-15:58 Chandola V, Banerjee A, Kumar V (2012) Anomaly detection for discrete sequences: a survey.  ... 
doi:10.1007/978-1-4899-7502-7_912-1 fatcat:mnxpfd3fg5et5htdqrmzrmrkhu

Big data analytics for preventive medicine

Muhammad Imran Razzak, Muhammad Imran, Guandong Xu
2019 Neural computing & applications (Print)  
We summarize state-of-the-art data analytics algorithms used for classification of disease, clustering (unusually high incidence of a particular disease), anomalies detection (detection of disease) and  ...  How can healthcare providers use modern data analytics tools and technologies to analyze and create value from complex data?  ...  Unsupervised is the commonly used method for anomalies detection and it does not require data labeling.  ... 
doi:10.1007/s00521-019-04095-y pmid:32205918 pmcid:PMC7088441 fatcat:x52upnuwbjdchkyb7hog5pvawm

Machine learning methods for detecting urinary tract infection and analysing daily living activities in people with dementia

Shirin Enshaeifar, Ahmed Zoha, Severin Skillman, Andreas Markides, Sahr Thomas Acton, Tarek Elsaleh, Mark Kenny, Helen Rostill, Ramin Nilforooshan, Payam Barnaghi, Jose M. Juarez
2019 PLoS ONE  
We have designed an algorithm to detect Urinary Tract Infections (UTI) which is one of the top five reasons of hospital admissions for people with dementia (around 9% of hospital admissions for people  ...  In addition, we have designed an algorithm for detecting changes in activity patterns to identify early symptoms of cognitive decline or health decline in order to provide personalised and preventative  ...  The data collected in the TIHM project will be available upon request and subject to ethics approval. All data requests to be sent to the sponsor's research department (research@sabp. nhs.uk).  ... 
doi:10.1371/journal.pone.0209909 pmid:30645599 pmcid:PMC6333356 fatcat:ymbof2altzf55cjunllyiafl6e

Anomaly Detection, Analysis and Prediction Techniques in IoT Environment: A Systematic Literature Review

Muhammad Fahim, Alberto Sillitti
2019 IEEE Access  
anomaly detection, prediction, and analysis.  ...  In this paper, we present the results of a systematic literature review about anomaly detection techniques except for these dominant research areas.  ...  One is designed over the discrete sequences while the other is designed for continuous time series of data.  ... 
doi:10.1109/access.2019.2921912 fatcat:k7pmdn6ruzevrpyibo7dmqh3ee

A Sequence Mining-Based Novel Architecture for Detecting Fraudulent Transactions in Healthcare Systems

Irum Matloob, Shoab Ahmed Khan, Rukaiya Rukaiya, Muazzam A. Khan Khattak, Arslan Munir
2022 IEEE Access  
This identifies anomalies as both sequences would not be compliant with the rule engine's sequences.  ...  This paper presents a novel process-based fraud detection methodology to detect insurance claim-related frauds in the healthcare system using sequence mining concepts.  ...  Most of the researches related to anomaly detection in healthcare have considered the clinical processes for a particular disease and utilized prior knowledge and applied the unsupervised models [16]  ... 
doi:10.1109/access.2022.3170888 fatcat:tf6tm4o4znf6zfsprhup5cn2ci

Anomaly Detection for Symbolic Time Series Representations of Reduced Dimensionality

Konstantinos Bountrogiannis, George Tzagkarakis, Panagiotis Tsakalides
2020 Zenodo  
From industrial to healthcare machines and wearable sensors, an unprecedented amount of data is becoming available for mining and information retrieval.  ...  In this paper, we propose a computationally efficient, yet highly accurate, framework for anomaly detection of streaming data in lower-dimensional spaces, utilizing a modification of the symbolic aggregate  ...  To address these issues, this work proposes an unsupervised, non-parametric method, characterized by low power and memory demands, for anomaly detection in unidimensional data, whereas guidelines for a  ... 
doi:10.5281/zenodo.4294535 fatcat:xgeuh4zx7fe5rnwpwjxjoyig24

A Unified Framework for Behaviour Monitoring and Abnormality Detection for Smart Home

Anupam Grewal, Maninder Kaur, Jong Hyuk Park
2019 Wireless Communications and Mobile Computing  
manually labelled classes along with the implementation of Local Outlier Factor method for detection of an abnormal pattern of the inhabitant of smart homes.  ...  The resultant frequent device utilization patterns with anomaly score more than the threshold value, reflecting abnormal activity patterns, are found more in evening time data in comparison to other time  ...  Data Discretization. Data discretization is data preprocessing technique [42] .  ... 
doi:10.1155/2019/1734615 fatcat:eg3wt5r5ireaxohssoejaubln4

Generating Artificial Sensor Data for the Comparison of Unsupervised Machine Learning Methods

Bernd Zimmering, Oliver Niggemann, Constanze Hasterok, Erik Pfannstiel, Dario Ramming, Julius Pfrommer
2021 Sensors  
Neural Net in anomaly detection.  ...  The data will pave the way for a comparison of selected machine learning methods in the exemplary field of unsupervised learning.  ...  Data Availability Statement: The data presented in this study are openly available in https://www. hsu-hh.de/imb/en/projects/ArtDataGen.  ... 
doi:10.3390/s21072397 pmid:33808459 fatcat:jeqndieva5arpco4hc43xeifmi

Data Mining for Wearable Sensors in Health Monitoring Systems: A Review of Recent Trends and Challenges

Hadi Banaee, Mobyen Ahmed, Amy Loutfi
2013 Sensors  
In particular, the paper outlines the more common data mining tasks that have been applied such as anomaly detection, prediction and decision making when considering in particular continuous time series  ...  This paper provides a recent review of the latest methods and algorithms used to analyze data from wearable sensors used for physiological monitoring of vital signs in healthcare services.  ...  Acknowledgements The authors of this work are partially supported by SAAPHO (Secure Active Aging: Participation and Health for the Old).  ... 
doi:10.3390/s131217472 pmid:24351646 pmcid:PMC3892855 fatcat:fy4hhounsrgffno2fclhanqt7m

Application of Data Mining Techniques to Healthcare Data

Mary K. Obenshain
2004 Infection control and hospital epidemiology  
AbstractA high-level introduction to data mining as it relates to surveillance of healthcare data is presented.  ...  A concrete example illustrates steps involved in the data mining process, and three successful data mining applications in the healthcare arena are described.  ...  Decision trees build classification rules and other mechanisms for detecting anomalies.  ... 
doi:10.1086/502460 pmid:15357163 fatcat:nyhq5bn74nchjc5tlvbvb4cuoq
« Previous Showing results 1 — 15 out of 831 results