{"id":13400470,"url":"https://github.com/pridiltal/ctv-AnomalyDetection","last_synced_at":"2025-03-14T06:31:40.559Z","repository":{"id":50569746,"uuid":"213264899","full_name":"pridiltal/ctv-AnomalyDetection","owner":"pridiltal","description":"CRAN Task View: Anomaly Detection with R  🛒🛒🛒🛒🛒🛒🛒🛒🛒🛒🛒🛒🛒🛍️🛒🛒","archived":false,"fork":false,"pushed_at":"2023-01-26T11:42:24.000Z","size":149,"stargazers_count":109,"open_issues_count":2,"forks_count":12,"subscribers_count":17,"default_branch":"master","last_synced_at":"2024-07-31T19:24:52.810Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"R","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pridiltal.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-10-07T00:22:28.000Z","updated_at":"2024-05-31T03:56:17.000Z","dependencies_parsed_at":"2023-02-14T17:01:18.353Z","dependency_job_id":null,"html_url":"https://github.com/pridiltal/ctv-AnomalyDetection","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pridiltal%2Fctv-AnomalyDetection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pridiltal%2Fctv-AnomalyDetection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pridiltal%2Fctv-AnomalyDetection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pridiltal%2Fctv-AnomalyDetection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pridiltal","download_url":"https://codeload.github.com/pridiltal/ctv-AnomalyDetection/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221440187,"owners_count":16821599,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-07-30T19:00:52.383Z","updated_at":"2024-10-25T16:30:30.212Z","avatar_url":"https://github.com/pridiltal.png","language":"R","funding_links":[],"categories":["R"],"sub_categories":[],"readme":"## CRAN Task View: Anomaly Detection with R\n\n                                                                     \n--------------- --------------------------------------------------   \n**Maintainer:** Priyanga Dilini Talagala, Rob J. Hyndman             \n**Contact:**    pritalagala at gmail.com                             \n**Version:**    2022-12-31                                           \n**URL:**        \u003chttps://CRAN.R-project.org/view=AnomalyDetection\u003e   \n\n\u003cdiv\u003e\n\nThis CRAN task view contains a list of packages that can be used for\nanomaly detection. Anomaly detection problems have many different facets\nand the detection techniques can be highly influenced by the way we\ndefine anomalies, the type of input data to the algorithm, the expected\noutput, etc. This leads to wide variations in problem formulations,\nwhich need to be addressed through different analytical approaches.\n\nAnomalies are often mentioned under several alternative names such as\noutliers, novelty, odd values, extreme values, faults, aberration in\ndifferent application domains. These variants are also considered for\nthis task view.\n\n**The development of this task view is fairly new and still in its early\nstages and therefore subject to changes. Please send suggestions for\nadditions and extensions for this task view to the task view\nmaintainer.**\n\n**Univariate Outlier Detection**\n\n  - *Univariate outlier* detection methods focus on values in a single\n    feature space. Package [univOutl](https://cran.r-project.org/package=univOutl)\n    includes various methods for detecting univariate outliers, e.g. the\n    Hidiroglou-Berthelot method. Methods to deal with skewed\n    distribution are also included in this package.\n  - The [dixonTest](https://cran.r-project.org/package=dixonTest) package provides\n    Dixon's ratio test for outlier detection in small and normally\n    distributed samples.\n  - Univariate outliers detection is also supported by `outlier()`\n    function in [GmAMisc](https://cran.r-project.org/package=GmAMisc) which\n    implements three different methods (mean-base, median-based,\n    boxplot-based).\n  - The [hotspots](https://cran.r-project.org/package=hotspots) package supports\n    univariate outlier detection by identifying values that are\n    disproportionately high based on both the deviance of any given\n    value from a statistical distribution and its similarity to other\n    values.\n  - The [outliers](https://cran.r-project.org/package=outliers) package provides a\n    collection of tests commonly used for identifying *outliers* . For\n    most functions the input is a numeric vector. If argument is a data\n    frame, then outlier is calculated for each column by sapply. The\n    same behavior is applied by apply when the matrix is given.\n  - The [extremevalues](https://cran.r-project.org/package=extremevalues) package\n    offers outlier detection and plot functions for univariate data. In\n    this work a value in the data is an outlier when it is unlikely to\n    be drawn from the estimated distribution.\n  - The [funModeling](https://cran.r-project.org/package=funModeling) package\n    provides tools for outlier detection using top/bottom X%, Tukey’s\n    boxplot definition and Hampel’s method.\n  - The [alphaOutlier](https://cran.r-project.org/package=alphaOutlier) package\n    provides Alpha-Outlier regions (as proposed by Davies and Gather\n    (1993)) for well-known probability distributions.\n\n**Multivariate Outlier Detection**\n\n  - Under *multivariate, high-dimensional or multidimensional scenario,*\n    where the focus is on n (\\\u003e2) - dimensional space, all attributes\n    might be of same type or might be a mixture of different types such\n    as categorical or numerical, which has a direct impact on the\n    implementation and scope of the algorithm. The problems of anomaly\n    detection in high-dimensional data are threefold, involving\n    detection of: (a) global anomalies, (b) local anomalies and (c)\n    micro clusters or clusters of anomalies. Global anomalies are very\n    different from the dense area with respect to their attributes. In\n    contrast, a local anomaly is only an anomaly when it is distinct\n    from, and compared with, its local neighbourhood. Micro clusters or\n    clusters of anomalies may cause masking problems.\n\n*Multivariate Outlier Detection: Density-based outlier detection*\n\n  - The [DDoutlier](https://cran.r-project.org/package=DDoutlier) package provides a\n    wide variety of distance- and density-based outlier detection\n    functions mainly focusing local outliers in high-dimensional data.\n  - *Local Outlier Factor (LOF)* is an algorithm for detecting anomalous\n    data points by measuring the local deviation of a given data point\n    with respect to its neighbours. This algorithm with some variations\n    is supported by many packages. The\n    [DescTools](https://cran.r-project.org/package=DescTools) package provides\n    functions for outlier detection using LOF and Tukey’s boxplot\n    definition. Functions `LOF()` and `GLOSH` in package\n    [dbscan](https://cran.r-project.org/package=dbscan) provide density based\n    anomaly detection methods using a kd-tree to speed up kNN search.\n    Parallel implementation of LOF which uses multiple CPUs to\n    significantly speed up the LOF computation for large datasets is\n    available in [Rlof](https://cran.r-project.org/package=Rlof) package. Package\n    [bigutilsr](https://cran.r-project.org/package=bigutilsr) provides utility\n    functions for outlier detection in large-scale data. It includes LOF\n    and outlier detection method based on departure from histogram.\n  - The [SMLoutliers](https://cran.r-project.org/package=SMLoutliers) package\n    provides an implementation of the Local Correlation Integral method\n    (Lof: Identifying density-based local outliers) for outlier\n    detection in multivariate data which consists of numeric values.\n  - The [ldbod](https://cran.r-project.org/package=ldbod) package provides flexible\n    functions for computing local density-based outlier scores. It\n    allows for subsampling of input data or a user specified reference\n    data set to compute outlier scores against, so both unsupervised and\n    semi-supervised outlier detection can be done.\n  - The [kernlab](https://cran.r-project.org/package=kernlab) package provides\n    kernel-based machine learning methods including one-class Support\n    Vector Machines for *novelty* detection.\n  - The [amelie](https://cran.r-project.org/package=amelie) package implements\n    anomaly detection as binary classification for multivariate\n  - The estimated density ratio function in\n    [densratio](https://cran.r-project.org/package=densratio) package can be used in\n    many applications such as anomaly detection, change-point detection,\n    covariate shift adaptation.\n  - The [lookout](https://cran.r-project.org/package=lookout) package detects\n    outliers using leave-one-out kernel density estimates and extreme\n    value theory. The bandwidth for kernel density estimates is computed\n    using persistent homology, a technique in topological data analysis.\n    It also has the capability to explore the birth and the cessation of\n    outliers with changing bandwidth and significance levels via\n    `persisting_outliers().`\n  - The Weighted BACON (blocked adaptive computationally-efficient\n    outlier nominators) algorithms in\n    [wbacon](https://cran.r-project.org/package=wbacon) implement a weighted variant\n    of the BACON algorithms for multivariate outlier detection and\n    robust linear regression. The methods assume that the typical data\n    follows an elliptically contoured distribution.\n\n*Multivariate Outlier Detection: Distance-based outlier detection*\n\n  - The [HDoutliers](https://cran.r-project.org/package=HDoutliers) package provides\n    an implementation of an algorithm for univariate and multivariate\n    outlier detection that can handle data with a mixed categorical and\n    continuous variables and outlier masking problem.\n  - The [stray](https://cran.r-project.org/package=stray) package implements an\n    algorithm for detecting anomalies in high-dimensional data that\n    addresses the limitations of 'HDoutliers' algorithm. An approach\n    based on extreme value theory is used for the anomalous threshold\n    calculation.\n  - The [Routliers](https://cran.r-project.org/package=Routliers) package provides\n    robust methods to detect univariate (Median Absolute Deviation\n    method) and multivariate outliers (Mahalanobis-Minimum Covariance\n    Determinant method).\n  - The [modi](https://cran.r-project.org/package=modi) package implements\n    Mahalanobis distance or depth-based algorithms for multivariate\n    outlier detection in the presence of missing values (incomplete\n    survey data).\n  - The\n    [CerioliOutlierDetection](https://cran.r-project.org/package=CerioliOutlierDetection)\n    package implements the iterated RMCD method of Cerioli (2010) for\n    multivariate outlier detection via robust Mahalanobis distances.\n  - The [rrcovHD](https://cran.r-project.org/package=rrcovHD) package performs\n    outlier identification using robust multivariate methods based on\n    robust mahalanobis distances and principal component analysis.\n  - The [mvoutlier](https://cran.r-project.org/package=mvoutlier) package also\n    provides various robust methods based multivariate outlier detection\n    capabilities. This includes a Mahalanobis type method with an\n    adaptive outlier cutoff value, a method incorporating local\n    neighborhood and a method for compositional data.\n  - Function `dm.mahalanobis` in [DJL](https://cran.r-project.org/package=DJL)\n    package implements Mahalanobis distance measure for outlier\n    detection. In addition to the basic distance measure, boxplots are\n    provided with potential outlier(s) to give an insight into the early\n    stage of data cleansing task.\n\n*Multivariate Outlier Detection: Clustering-based outlier detection*\n\n  - The [kmodR](https://cran.r-project.org/package=kmodR) package presents a unified\n    approach for simultaneously clustering and discovering outliers in\n    high dimensional data. Their approach is formalized as a\n    generalization of the k-MEANS problem.\n  - The [DMwR2](https://cran.r-project.org/package=DMwR2) package uses hierarchical\n    clustering to obtain a ranking of outlierness for a set of cases.\n    The ranking is obtained on the basis of the path each case follows\n    within the merging steps of a agglomerative hierarchical clustering\n    method.\n\n*Multivariate Outlier Detection: Angle-based outlier detection*\n\n  - The [abodOutlier](https://cran.r-project.org/package=abodOutlier) package\n    performs angle-based outlier detection on high dimensional data. A\n    complete, a randomized and a knn based methods are available.\n\n*Multivariate Outlier Detection: Decision tree based approaches*\n\n  - Explainable outlier detection method through decision tree\n    conditioning is facilitated by\n    [outliertree](https://cran.r-project.org/package=outliertree) package .\n  - The\n    [bagged.outliertrees](https://cran.r-project.org/package=bagged.outliertrees)\n    package provides an explainable unsupervised outlier detection\n    method based on an ensemble implementation of the existing\n    OutlierTree procedure in\n    [outliertree](https://cran.r-project.org/package=outliertree) package. The\n    implementation takes advantage of bootstrap aggregating (bagging) to\n    improve robustness by reducing the possible masking effect and\n    subsequent high variance (similarly to Isolation Forest), hence the\n    name \"Bagged OutlierTrees\".\n  - The [isotree](https://cran.r-project.org/package=isotree) package provides fast\n    and multi-threaded implementation of Extended Isolation Forest,\n    Fair-Cut Forest, SCiForest (a.k.a. Split-Criterion iForest), and\n    regular Isolation Forest, for isolation-based outlier detection,\n    clustered outlier detection, distance or similarity approximation,\n    and imputation of missing values based on random or guided decision\n    tree splitting. It also supports categorical data.\n  - The [outForest](https://cran.r-project.org/package=outForest) package provides a\n    random forest based implementation for multivariate outlier\n    detection. In this method each numeric variable is regressed onto\n    all other variables by a random forest. If the scaled absolute\n    difference between observed value and out-of-bag prediction of the\n    corresponding random forest is suspiciously large, then a value is\n    considered an outlier.\n  - The [solitude](https://cran.r-project.org/package=solitude) package provides an\n    implementation of Isolation forest which detects anomalies in\n    cross-sectional tabular data purely based on the concept of\n    isolation without employing any distance or density measures.\n\n*Multivariate Outlier Detection: Other approaches*\n\n  - The [abnormality](https://cran.r-project.org/package=abnormality) package\n    measures a Subject's Abnormality with Respect to a Reference\n    Population. A methodology is introduced to address this bias to\n    accurately measure overall abnormality in high dimensional spaces.\n    It can be applied to datasets in which the number of observations is\n    less than the number of features/variables, and it can be abstracted\n    to practically any number of domains or dimensions.\n  - The [ICSOutlier](https://cran.r-project.org/package=ICSOutlier) package performs\n    multivariate outlier detection using invariant coordinates and\n    offers different methods to choose the appropriate components. The\n    current implementation targets data sets with only a small\n    percentage of outliers but future extensions are under preparation.\n  - The [sGMRFmix](https://cran.r-project.org/package=sGMRFmix) package provides an\n    anomaly detection method for multivariate noisy sensor data using\n    sparse Gaussian Markov random field mixtures. It can compute\n    variable-wise anomaly scores.\n  - Artificial neural networks for anomaly detection is implemented in\n    [ANN2](https://cran.r-project.org/package=ANN2) package.\n  - The [probout](https://cran.r-project.org/package=probout) package estimates\n    unsupervised outlier probabilities for multivariate numeric\n  - The [mrfDepth](https://cran.r-project.org/package=mrfDepth) package provides\n    tools to compute depth measures and implementations of related tasks\n    such as outlier detection, data exploration and classification of\n    multivariate, regression and functional data.\n  - The [evtclass](https://cran.r-project.org/package=evtclass) package provides two\n    classifiers for open set recognition and novelty detection based on\n    extreme value theory.\n  - The [FastHCS](https://cran.r-project.org/package=FastHCS) package implements\n    robust algorithm for principal component analysis and thereby\n    provide robust PCA modeling and associated outlier detection and\n    diagnostic tools for high-dimensional data. PCA based outlier\n    detection tools are also available via\n    [FactoInvestigate](https://cran.r-project.org/package=FactoInvestigate) package.\n  - *Cellwise outliers* are entries in the data matrix which are\n    substantially higher or lower than what could be expected based on\n    the other cells in its column as well as the other cells in its row,\n    taking the relations between the columns into account. Package\n    [cellWise](https://cran.r-project.org/package=cellWise) provides tools for\n    detecting cellwise outliers and robust methods to analyze data which\n    may contain them.\n  - *The Projection Congruent Subset (PCS)* is a method for finding\n    multivariate outliers by searching for a subset which minimizes a\n    criterion. PCS is supported by\n    [FastPCS](https://cran.r-project.org/package=FastPCS) package.\n  - The [molic](https://cran.r-project.org/package=molic) package provides an\n    outlier detection method for high‐dimensional contingency tables\n    using decomposable graphical models\n  - The [outlierensembles](https://cran.r-project.org/package=outlierensembles)\n    package provides ensemble functions for outlier/anomaly detection.\n    In addition to some exiting ensemble methods for outlier detcetion,\n    it also provides an Item Response Theory based ensemble method.\n\n**Temporal Data**\n\n  - The problems of anomaly detection for temporal data are 3-fold: (a)\n    the detection of contextual anomalies (point anomalies) within a\n    given series; (b) the detection of anomalous subsequences within a\n    given series; and (c) the detection of anomalous series within a\n    collection of series\n  - The [trendsegmentR](https://cran.r-project.org/package=trendsegmentR) package\n    performs the detection of point anomalies and linear trend changes\n    for univariate time series by implementing the bottom-up unbalanced\n    wavelet transformation.\n  - The [anomaly](https://cran.r-project.org/package=anomaly) package implements\n    Collective And Point Anomaly (CAPA), Multi-Variate Collective And\n    Point Anomaly (MVCAPA), Proportion Adaptive Segment Selection (PASS)\n    and Bayesian Abnormal Region Detector (BARD) methods for the\n    detection of *anomalies* in time series data.\n  - The [anomalize](https://cran.r-project.org/package=anomalize) package enables a\n    \"tidy\" workflow for detecting anomalies in data. The main functions\n    are `time_decompose()`, `anomalize()`, and `time_recompose()`.\n  - The [cbar](https://cran.r-project.org/package=cbar) package detect contextual\n    anomalies in time-series data with Bayesian data analysis. It\n    focuses on determining a normal range of target value, and provides\n    simple-to-use functions to abstract the outcome.\n  - The `detectAO` and `detectIO` functions in\n    [TSA](https://cran.r-project.org/package=TSA) package support detecting additive\n    outlier and innovative outlier in time series data.\n  - The [washeR](https://cran.r-project.org/package=washeR) package performs time\n    series outlier detection using non parametric test. An input can be\n    a data frame (grouped time series: phenomenon+date+group+values) or\n    a vector (single time series)\n  - The [tsoutliers](https://cran.r-project.org/package=tsoutliers) package\n    implements the Chen-Liu approach for detection of time series\n    outliers such as innovational outliers, additive outliers, level\n    shifts, temporary changes and seasonal level shifts.\n  - The [seasonal](https://cran.r-project.org/package=seasonal) package provides\n    easy-to-use interface to X-13-ARIMA-SEATS, the seasonal adjustment\n    software by the US Census Bureau. It offers full access to almost\n    all options and outputs of X-13, including outlier detection.\n  - The [npphen](https://cran.r-project.org/package=npphen) package implements basic\n    and high-level functions for detection of anomalies in vector data\n    (numerical series/ time series) and raster data (satellite derived\n    products). Processing of very large raster files is supported.\n  - the [ACA](https://cran.r-project.org/package=ACA) package offers an interactive\n    function for the detection of abrupt change-points or aberrations in\n    point series.\n  - A set of online fault (anomaly) detectors for time series using\n    prediction-based and window-based techniques are available via\n    [otsad](https://cran.r-project.org/package=otsad) package. It can handle both\n    stationary and non-stationary environments.\n  - The [oddstream](https://cran.r-project.org/package=oddstream) package implements\n    an algorithm for early detection of anomalous series within a large\n    collection of streaming time series data. The model uses time series\n    features as inputs, and a density-based comparison to detect any\n    significant changes in the distribution of the features.\n  - The [composits](https://cran.r-project.org/package=composits) package provides\n    an ensemble of time series outlier detection methods that can be\n    used for compositional, multivariate and univariate data. It uses\n    the four R packages [forecast](https://cran.r-project.org/package=forecast),\n    [tsoutliers](https://cran.r-project.org/package=tsoutliers),\n    [otsad](https://cran.r-project.org/package=otsad) and\n    [anomalize](https://cran.r-project.org/package=anomalize) to detect time series\n    outliers.\n  - The [pasadr](https://cran.r-project.org/package=pasadr) package provides a novel\n    stealthy-attack detection mechanism that monitors time series of\n    sensor measurements in real time for structural changes in the\n    process behavior. It has the capability of detecting both\n    significant deviations in the process behavior and subtle\n    attack-indicating changes, significantly raising the bar for\n    strategic adversaries who may attempt to maintain their malicious\n    manipulation within the noise level.\n\n**Spatial Outliers**\n\n  - Spatial objects whose non-spatial attribute values are markedly\n    different from those of their spatial neighbors are known as Spatial\n    outliers or abnormal spatial patterns.\n  - The [RWBP](https://cran.r-project.org/package=RWBP) package detects spatial\n    outliers using a Random Walk on Bipartite Graph.\n  - Enhanced False Discovery Rate (EFDR) is a tool to detect anomalies\n    in an image. Package [EFDR](https://cran.r-project.org/package=EFDR) implements\n    wavelet-based Enhanced FDR for detecting signals from complete or\n    incomplete spatially aggregated data. The package also provides\n    elementary tools to interpolate spatially irregular data onto a grid\n    of the required size.\n  - The function `spatial.outlier` in\n    [depth.plot](https://cran.r-project.org/package=depth.plot) package helps to\n    identify multivariate spatial outlier within a p-variate data cloud\n    or if any p-variate observation is an outlier with respect to a\n    p-variate data cloud.\n\n**Spatio-Temporal Data**\n\n  - Functions for error detection and correction in point data quality\n    datasets that are used in species distribution modeling are\n    available via [biogeo](https://cran.r-project.org/package=biogeo) package.\n  - The [CoordinateCleaner](https://cran.r-project.org/package=CoordinateCleaner)\n    package provides functions for flagging of common spatial and\n    temporal outliers (errors) in biological and paleontological\n    collection data, for the use in conservation, ecology and\n    paleontology.\n\n**Functional Data**\n\n  - The `foutliers()` function from\n    [rainbow](https://cran.r-project.org/package=rainbow) package provides\n    functional outlier detection methods. Bagplots and boxplots for\n    functional data can also be used to identify outliers, which have\n    either the lowest depth (distance from the centre) or the lowest\n    density, respectively.\n  - The [adamethods](https://cran.r-project.org/package=adamethods) package provides\n    a collection of several algorithms to obtain archetypoids with small\n    and large databases and with both classical multivariate data and\n    functional data (univariate and multivariate). Some of these\n    algorithms also allow to detect anomalies.\n  - The `shape.fd.outliers` function in\n    [ddalpha](https://cran.r-project.org/package=ddalpha) package detects functional\n    outliers of first three orders, based on the order extended\n    integrated depth for functional data.\n  - The [fda.usc](https://cran.r-project.org/package=fda.usc) package provides tools\n    for outlier detection in functional data (atypical curves detection)\n    using different approaches such as likelihood ratio test, depth\n    measures, quantiles of the bootstrap samples.\n  - The [fdasrvf](https://cran.r-project.org/package=fdasrvf) package supports\n    outlier detection in functional data using the square-root velocity\n    framework which allows for elastic analysis of functional data\n    through phase and amplitude separation.\n  - The [fdaoutlier](https://cran.r-project.org/package=fdaoutlier) package provides\n    a collection of functions for outlier detection in functional data\n    analysis. Methods implemented include directional outlyingness,\n    MS-plot, total variation depth, and sequential transformations among\n    others.\n\n**Visualization of Anomalies**\n\n  - The [OutliersO3](https://cran.r-project.org/package=OutliersO3) package provides\n    tools to aid in the display and understanding of patterns of\n    multivariate outliers. It uses the results of identifying outliers\n    for every possible combination of dataset variables to provide\n    insight into why particular cases are outliers.\n  - The [Morpho](https://cran.r-project.org/package=Morpho) package provides a\n    collection of tools for Geometric Morphometrics and mesh processing.\n    Apart from the core functions it provides a graphical interface to\n    find outliers and/or to switch mislabeled landmarks.\n  - The [StatDA](https://cran.r-project.org/package=StatDA) package provides\n    visualization tools to locate outliers in environmental data.\n\n**Pre-processing Methods for Anomaly Detection**\n\n  - The [dobin](https://cran.r-project.org/package=dobin) package provides dimension\n    reduction technique for outlier detection using neighbours,\n    constructs a set of basis vectors for outlier detection. It brings\n    outliers to the fore-front using fewer basis vectors.\n\n**Specific Application Fields**\n\n*Epidemiology*\n\n  - The [ABPS](https://cran.r-project.org/package=ABPS) package provides an\n    implementation of the Abnormal Blood Profile Score (ABPS, part of\n    the Athlete Biological Passport program of the World Anti-Doping\n    Agency), which combines several blood parameters into a single score\n    in order to detect blood doping. The package also contains functions\n    to calculate other scores used in anti-doping programs, such as the\n    OFF-score\n  - The [surveillance](https://cran.r-project.org/package=surveillance) package\n    implements statistical methods for aberration detection in time\n    series of counts, proportions and categorical data, as well as for\n    the modeling of continuous-time point processes of epidemic\n    phenomena. The package also contains several real-world data sets,\n    the ability to simulate outbreak data, and to visualize the results\n    of the monitoring in a temporal, spatial or spatio-temporal fashion.\n  - The [outbreaker2](https://cran.r-project.org/package=outbreaker2) package\n    supports Bayesian reconstruction of disease outbreaks using\n    epidemiological and genetic information. It is applicable to various\n    densely sampled epidemics, and improves previous approaches by\n    detecting unobserved and imported cases, as well as allowing\n    multiple introductions of the pathogen.\n  - The [outbreaks](https://cran.r-project.org/package=outbreaks) package provides\n    empirical or simulated disease outbreak data, either as RData or as\n    text files.\n\n*Other*\n\n  - The [precintcon](https://cran.r-project.org/package=precintcon) package contains\n    functions to analyze the precipitation intensity, concentration and\n    anomaly.\n  - The [survBootOutliers](https://cran.r-project.org/package=survBootOutliers)\n    package provides concordance based bootstrap methods for outlier\n    detection in survival analysis.\n  - The [pcadapt](https://cran.r-project.org/package=pcadapt) package provides\n    methods to detect genetic markers involved in biological adaptation\n    using statistical tools based on Principal Component Analysis.\n  - The [rgr](https://cran.r-project.org/package=rgr) package supports exploratory\n    data analysis with applied geochemical data, with special\n    application to the estimation of background ranges and\n    identification of anomalies to support mineral exploration and\n    environmental studies.\n  - The [NMAoutlier](https://cran.r-project.org/package=NMAoutlier) package\n    implements the forward search algorithm for the detection of\n    outlying studies (studies with extreme results) in network\n    meta-analysis.\n  - The [boutliers](https://cran.r-project.org/package=boutliers) package provides\n    methods for outlier detection and influence diagnostics for\n    meta-analysis based on Bootstrap distributions of the influence\n    statistics.\n  - The [dave](https://cran.r-project.org/package=dave) package provides a\n    collection of functions for data analysis in vegetation ecology\n    including outlier detection using nearest neighbour distances.\n  - The [MALDIrppa](https://cran.r-project.org/package=MALDIrppa) package provides\n    methods for quality control and robust pre-processing and analysis\n    of MALDI mass spectrometry data.\n  - The [MIPHENO](https://cran.r-project.org/package=MIPHENO) package contains\n    functions to carry out processing of high throughput data analysis\n    and detection of putative hits/mutants.\n  - The [OutlierDM](https://cran.r-project.org/package=OutlierDM) package provides\n    functions to detect outlying values such as genes, peptides or\n    samples for multi-replicated high-throughput high-dimensional data.\n  - The [qpcR](https://cran.r-project.org/package=qpcR) package implements methods\n    for kinetic outlier detection (KOD) in real-time polymerase chain\n    reaction (qPCR).\n  - The [referenceIntervals](https://cran.r-project.org/package=referenceIntervals)\n    package provides a collection of tools including outlier detcetion\n    to allow the medical professional to calculate appropriate reference\n    ranges (intervals) with confidence intervals around the limits for\n    diagnostic purposes.\n  - The Hampel filter is a robust outlier detector using Median Absolute\n    Deviation (MAD). The\n    [seismicRoll](https://cran.r-project.org/package=seismicRoll) package provides\n    fast rolling functions for seismology including outlier detection\n    with a rolling Hampel Filter.\n  - The [spikes](https://cran.r-project.org/package=spikes) package provides tool to\n    detect election fraud from irregularities in vote-share\n    distributions using re-sampled kernel density method.\n  - The [wql](https://cran.r-project.org/package=wql) package stands for \\`water\n    quality' provides functions including anomaly detection to assist in\n    the processing and exploration of data from environmental monitoring\n    programs.\n  - The Grubbs‐Beck test is recommended by the federal guidelines for\n    detection of low outliers in flood flow frequency computation in the\n    United States. The [MGBT](https://cran.r-project.org/package=MGBT) computes the\n    multiple Grubbs-Beck low-outlier test on positively distributed data\n    and utilities for non-interpretive U.S. Geological Survey annual\n    peak-stream flow data processing.\n  - The [envoutliers](https://cran.r-project.org/package=envoutliers) package\n    provides three semi-parametric methods for detection of outliers in\n    environmental data based on kernel regression and subsequent\n    analysis of smoothing residuals\n  - The [rIP](https://cran.r-project.org/package=rIP) package supports detection of\n    fraud in online surveys by tracing, scoring, and visualizing IP\n    addresses\n  - The [extremeIndex](https://cran.r-project.org/package=extremeIndex) computes an\n    index measuring the amount of information brought by forecasts for\n    extreme events, subject to calibration. This index is originally\n    designed for weather or climate forecasts, but it may be used in\n    other forecasting contexts.\n  - The [clampSeg](https://cran.r-project.org/package=clampSeg) package provides\n    tool to identify and idealize flickering events in filtered ion\n    channel recordings.\n\n**Data Sets**\n\n  - The [anomaly](https://cran.r-project.org/package=anomaly) package contains\n    lightcurve time series data from the Kepler telescope.\n  - The [leri](https://cran.r-project.org/package=leri) package finds and downloads\n    Landscape Evaporative Response Index (LERI) data, then reads the\n    data into R. The LERI product measures anomalies in actual\n    evapotranspiration, to support drought monitoring and early warning\n    systems.\n  - The [waterData](https://cran.r-project.org/package=waterData) package imports\n    U.S. Geological Survey (USGS) daily hydrologic data from USGS web\n    services and provides functions to calculate and plot anomalies.\n\n**Miscellaneous**\n\n  - The [CircOutlier](https://cran.r-project.org/package=CircOutlier) package\n    enables detection of outliers in circular-circular regression\n    models, modifying its and estimating of models parameters.\n  - The Residual Congruent Subset (RCS) is a method for finding outliers\n    in the regression setting. RCS is supported by\n    [FastRCS](https://cran.r-project.org/package=FastRCS) package.\n  - Package [quokar](https://cran.r-project.org/package=quokar) provides quantile\n    regression outlier diagnostics with K Left Out Analysis.\n  - The [oclust](https://cran.r-project.org/package=oclust) package provides a\n    function to detect and trim outliers in Gaussian mixture model based\n    clustering using methods described in Clark and McNicholas (2019).\n  - The [semdiag](https://cran.r-project.org/package=semdiag) package implements\n    outlier and leverage diagnostics for Structural equation modeling.\n  - The [SeleMix](https://cran.r-project.org/package=SeleMix) package provides\n    functions for detection of outliers and influential errors using a\n    latent variable model. A mixture model (Gaussian contamination\n    model) based on response(s) y and a depended set of covariates is\n    fit to the data to quantify the impact of errors to the estimates.\n  - The [compositions](https://cran.r-project.org/package=compositions) package\n    provides functions to detect various types of outliers in\n    compositional datasets.\n  - The [kuiper.2samp](https://cran.r-project.org/package=kuiper.2samp) package\n    performs the two-sample Kuiper test to assess the anomaly of\n    continuous, one-dimensional probability distributions.\n  - The `enpls.od()` function in [enpls](https://cran.r-project.org/package=enpls)\n    package performs outlier detection with ensemble partial least\n    squares.\n  - The [surveyoutliers](https://cran.r-project.org/package=surveyoutliers) package\n    helps manage outliers in sample surveys by calculating optimal\n    one-sided winsorizing cutoffs.\n  - The [faoutlier](https://cran.r-project.org/package=faoutlier) package provides\n    tools for detecting and summarize influential cases that can affect\n    exploratory and confirmatory factor analysis models and structural\n    equation models.\n  - The [crseEventStudy](https://cran.r-project.org/package=crseEventStudy) package\n    provides a robust and powerful test of abnormal stock returns in\n    long-horizon event\n    studies\n\n\u003c/div\u003e\n\n### CRAN packages:\n\n  - [abnormality](https://cran.r-project.org/package=abnormality)\n  - [abodOutlier](https://cran.r-project.org/package=abodOutlier)\n  - [ABPS](https://cran.r-project.org/package=ABPS)\n  - [ACA](https://cran.r-project.org/package=ACA)\n  - [adamethods](https://cran.r-project.org/package=adamethods)\n  - [alphaOutlier](https://cran.r-project.org/package=alphaOutlier)\n  - [amelie](https://cran.r-project.org/package=amelie)\n  - [ANN2](https://cran.r-project.org/package=ANN2)\n  - [anomalize](https://cran.r-project.org/package=anomalize)\n  - [anomaly](https://cran.r-project.org/package=anomaly)\n  - [bagged.outliertrees](https://cran.r-project.org/package=bagged.outliertrees)\n  - [bigutilsr](https://cran.r-project.org/package=bigutilsr)\n  - [biogeo](https://cran.r-project.org/package=biogeo)\n  - [boutliers](https://cran.r-project.org/package=boutliers)\n  - [cbar](https://cran.r-project.org/package=cbar)\n  - [cellWise](https://cran.r-project.org/package=cellWise)\n  - [CerioliOutlierDetection](https://cran.r-project.org/package=CerioliOutlierDetection)\n  - [CircOutlier](https://cran.r-project.org/package=CircOutlier)\n  - [clampSeg](https://cran.r-project.org/package=clampSeg)\n  - [compositions](https://cran.r-project.org/package=compositions)\n  - [composits](https://cran.r-project.org/package=composits)\n  - [CoordinateCleaner](https://cran.r-project.org/package=CoordinateCleaner)\n  - [crseEventStudy](https://cran.r-project.org/package=crseEventStudy)\n  - [dave](https://cran.r-project.org/package=dave)\n  - [dbscan](https://cran.r-project.org/package=dbscan)\n  - [ddalpha](https://cran.r-project.org/package=ddalpha)\n  - [DDoutlier](https://cran.r-project.org/package=DDoutlier) (core)\n  - [densratio](https://cran.r-project.org/package=densratio)\n  - [depth.plot](https://cran.r-project.org/package=depth.plot)\n  - [DescTools](https://cran.r-project.org/package=DescTools)\n  - [dixonTest](https://cran.r-project.org/package=dixonTest)\n  - [DJL](https://cran.r-project.org/package=DJL)\n  - [DMwR2](https://cran.r-project.org/package=DMwR2)\n  - [dobin](https://cran.r-project.org/package=dobin)\n  - [EFDR](https://cran.r-project.org/package=EFDR)\n  - [enpls](https://cran.r-project.org/package=enpls)\n  - [envoutliers](https://cran.r-project.org/package=envoutliers)\n  - [evtclass](https://cran.r-project.org/package=evtclass)\n  - [extremeIndex](https://cran.r-project.org/package=extremeIndex)\n  - [extremevalues](https://cran.r-project.org/package=extremevalues)\n  - [FactoInvestigate](https://cran.r-project.org/package=FactoInvestigate)\n  - [faoutlier](https://cran.r-project.org/package=faoutlier)\n  - [FastHCS](https://cran.r-project.org/package=FastHCS)\n  - [FastPCS](https://cran.r-project.org/package=FastPCS)\n  - [FastRCS](https://cran.r-project.org/package=FastRCS)\n  - [fda.usc](https://cran.r-project.org/package=fda.usc)\n  - [fdaoutlier](https://cran.r-project.org/package=fdaoutlier)\n  - [fdasrvf](https://cran.r-project.org/package=fdasrvf)\n  - [forecast](https://cran.r-project.org/package=forecast)\n  - [funModeling](https://cran.r-project.org/package=funModeling)\n  - [GmAMisc](https://cran.r-project.org/package=GmAMisc)\n  - [HDoutliers](https://cran.r-project.org/package=HDoutliers) (core)\n  - [hotspots](https://cran.r-project.org/package=hotspots)\n  - [ICSOutlier](https://cran.r-project.org/package=ICSOutlier)\n  - [isotree](https://cran.r-project.org/package=isotree)\n  - [kernlab](https://cran.r-project.org/package=kernlab)\n  - [kmodR](https://cran.r-project.org/package=kmodR)\n  - [kuiper.2samp](https://cran.r-project.org/package=kuiper.2samp)\n  - [ldbod](https://cran.r-project.org/package=ldbod)\n  - [leri](https://cran.r-project.org/package=leri)\n  - [lookout](https://cran.r-project.org/package=lookout)\n  - [MALDIrppa](https://cran.r-project.org/package=MALDIrppa)\n  - [MGBT](https://cran.r-project.org/package=MGBT)\n  - [MIPHENO](https://cran.r-project.org/package=MIPHENO)\n  - [modi](https://cran.r-project.org/package=modi)\n  - [molic](https://cran.r-project.org/package=molic)\n  - [Morpho](https://cran.r-project.org/package=Morpho)\n  - [mrfDepth](https://cran.r-project.org/package=mrfDepth)\n  - [mvoutlier](https://cran.r-project.org/package=mvoutlier)\n  - [NMAoutlier](https://cran.r-project.org/package=NMAoutlier)\n  - [npphen](https://cran.r-project.org/package=npphen)\n  - [oclust](https://cran.r-project.org/package=oclust)\n  - [oddstream](https://cran.r-project.org/package=oddstream)\n  - [otsad](https://cran.r-project.org/package=otsad)\n  - [outbreaker2](https://cran.r-project.org/package=outbreaker2)\n  - [outbreaks](https://cran.r-project.org/package=outbreaks)\n  - [outForest](https://cran.r-project.org/package=outForest)\n  - [OutlierDM](https://cran.r-project.org/package=OutlierDM)\n  - [outlierensembles](https://cran.r-project.org/package=outlierensembles)\n  - [outliers](https://cran.r-project.org/package=outliers)\n  - [OutliersO3](https://cran.r-project.org/package=OutliersO3) (core)\n  - [outliertree](https://cran.r-project.org/package=outliertree)\n  - [pasadr](https://cran.r-project.org/package=pasadr)\n  - [pcadapt](https://cran.r-project.org/package=pcadapt)\n  - [precintcon](https://cran.r-project.org/package=precintcon)\n  - [probout](https://cran.r-project.org/package=probout)\n  - [qpcR](https://cran.r-project.org/package=qpcR)\n  - [quokar](https://cran.r-project.org/package=quokar)\n  - [rainbow](https://cran.r-project.org/package=rainbow)\n  - [referenceIntervals](https://cran.r-project.org/package=referenceIntervals)\n  - [rgr](https://cran.r-project.org/package=rgr)\n  - [rIP](https://cran.r-project.org/package=rIP)\n  - [Rlof](https://cran.r-project.org/package=Rlof)\n  - [Routliers](https://cran.r-project.org/package=Routliers)\n  - [rrcovHD](https://cran.r-project.org/package=rrcovHD)\n  - [RWBP](https://cran.r-project.org/package=RWBP)\n  - [seasonal](https://cran.r-project.org/package=seasonal)\n  - [seismicRoll](https://cran.r-project.org/package=seismicRoll)\n  - [SeleMix](https://cran.r-project.org/package=SeleMix)\n  - [semdiag](https://cran.r-project.org/package=semdiag)\n  - [sGMRFmix](https://cran.r-project.org/package=sGMRFmix)\n  - [SMLoutliers](https://cran.r-project.org/package=SMLoutliers)\n  - [solitude](https://cran.r-project.org/package=solitude)\n  - [spikes](https://cran.r-project.org/package=spikes)\n  - [StatDA](https://cran.r-project.org/package=StatDA)\n  - [stray](https://cran.r-project.org/package=stray)\n  - [survBootOutliers](https://cran.r-project.org/package=survBootOutliers)\n  - [surveillance](https://cran.r-project.org/package=surveillance)\n  - [surveyoutliers](https://cran.r-project.org/package=surveyoutliers)\n  - [trendsegmentR](https://cran.r-project.org/package=trendsegmentR)\n  - [TSA](https://cran.r-project.org/package=TSA)\n  - [tsoutliers](https://cran.r-project.org/package=tsoutliers)\n  - [univOutl](https://cran.r-project.org/package=univOutl)\n  - [washeR](https://cran.r-project.org/package=washeR)\n  - [waterData](https://cran.r-project.org/package=waterData)\n  - [wbacon](https://cran.r-project.org/package=wbacon)\n  - [wql](https://cran.r-project.org/package=wql)\n\n### Related links:\n\n  - CRAN Task View: [Cluster](Cluster.html)\n  - CRAN Task View: [ExtremeValue](ExtremeValue.html)\n  - [GitHub repository for this Task\n    View](https://github.com/pridiltal/ctv-AnomalyDetection)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpridiltal%2Fctv-AnomalyDetection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpridiltal%2Fctv-AnomalyDetection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpridiltal%2Fctv-AnomalyDetection/lists"}