local outlier factor (LOF)

In the age of smart manufacturing, there are typically multitude of sensors that are connected to each assembly line. The amount of data generated could be used to create a digital twin model of the complete process; wherein virtual replicas of the device and the process can be created before and during the process. An important aspect is automatic anomaly detection in the manufacturing process. Anomaly/outlier detection identifies data-points, events and/or observations that deviate from the dataset's normal behaviour. A major problem in predicting anomaly from datasets is the limited accuracy that can be achieved. Several state-of-the-art techniques provide very high accuracy (>95%). However, these result in a considerable increase in the required time, thereby limiting its use to non-real-time applications. This paper proposes a cluster-aided two-step (CATS) approach for anomaly detection wherein two unsupervised detection techniques are employed in serial. The technique used for the first step is density-based spatial clustering for applications with noise (DBSCAN), while the second technique is local outlier factor (LOF). The output of the first-step technique is fed to the second technique, thereby utilizing the knowledge generated in the first step. An extensive simulation analysis indicates that the proposed CATS algorithm results in >95% accuracy for the outlier population is above 15% with a prediction time of lesser than 85 s.

A single outlier detection procedure for data generated from BL(1,1,1,1) models is developed. It is carried out in three stages. Firstly, the measure of impact of an IO and AO denoted by IO ω , AO ω , respectively are derived based on least squares method. Secondly, test statistics and test criteria are defined for classifying an observation as an outlier of its respective type. Finally, a general single outlier detection procedure is presented to distinguish a particular type of outlier at a time point t.

Outlier Detection is a Data Mining Application. Outlier contains noisy data which is researched in various domains. The various techniques are already being researched that is more generic. We surveyed on various techniques and applications of outlier detection that provides a novel approach that is more useful for the beginners. The proposed approach helps to clean data at university level in less time with great accuracy. This survey includes the existing outlier techniques and applications where the noisy data exists. Our paper defines critical review on various techniques used in different applications of outlier detection that are to be researched further and they gives a particular type of knowledge based data i.e. more useful in research activities. So where the Anomalies is present it will be detected through outlier detection techniques and monitored accordingly especially in educational Data Mining.

Random Forest (RF) is an ensemble classification technique that was developed by Breiman over a decade ago. Compared with other ensemble techniques, it has proved its accuracy and superiority. Many researchers, however, believe that there is still room for enhancing and improving its performance in terms of predictive accuracy. This explains why, over the past decade, there have been many extensions of RF where each extension employed a variety of techniques and strategies to improve certain aspect(s) of RF. Since it has been proven empirically that ensembles tend to yield better results when there is a significant diversity among the constituent models, the objective of this paper is twofolds. First, it investigates how an unsupervised learning technique, namely, Local Outlier Factor (LOF) can be used to identify diverse trees in the RF. Second, trees with the highest LOF scores are then used to produce an extension of RF termed LOFB-DRF that is much smaller in size than RF, and yet performs at least as good as RF, but mostly exhibits higher performance in terms of accuracy. The latter refers to a known technique called ensemble pruning. Experimental results on 10 real datasets prove the superiority of our proposed extension over the traditional RF. Unprecedented pruning levels reaching as high as 99% have been achieved at the time of boosting the predictive accuracy of the ensemble. The notably high pruning level makes the technique a good candidate for real-time applications.

An outlier ranking tree selection approach to extreme pruning of random forests. FAWAGREH, K., GABER, M.M. and ELYAN, E. 2016. An outlier ranking tree selection approach to extreme pruning of random forests. In Jayne, C. and Iliadis, L. (eds.) Communications in computer and information science, 629, Engineering applications of neural networks: proceedings of the 17th international conference on engineering applications of neural networks (EANN 2016), 2-

Thompson's partition of a cyclic subnormal operator into normal and completely non-normal components is combined with a noncommutative calculus for hyponormal operators for separating outliers from the cloud, in rather general point distributions in the plane. The main result provides exact transformation formulas from the power moments of the prescribed point distribution into the moments of the uniform mass carried by the cloud. The proposed algorithm solely depends on the Hessenberg matrix associated to the original data. The robustness of the algorithm is reflected by the insensitivity of the output under trace class, or by a theorem of Voiculescu, under certain Hilbert-Schmidt class, additive perturbations of the Hessenberg matrix.

Feature Selection is the preprocessing process of identifying the subset of data from large dimension data. To identifying the required data, using some Feature Selection algorithms. Like Relief, Parzen-Relief algorithms, it attempts to directly maximize the classification accuracy and naturally reflects the Bayes error in the objective. Proposed algorithmic framework selects a subset of features by minimizing the Bayes error rate estimated by a nonparametric estimator. As an example, we show that the Relief algorithm greedily attempts to minimize the Bayes error estimated by the k-Nearest-Neighbor (kNN) method. In particular, by exploiting the proposed framework, we establish the Parzen-Relief (P-Relief) algorithm based on Parzen window estimator. The Relief algorithm is a popular approach for feature weight estimation. Many extensions of the Relief algorithm are developed. Because of the randomicity and the uncertainty of the instances used for calculating the feature weight vecto...

Outlier, or anomaly, detection is essential for optimal performance of machine learning methods and statistical predictive models. It is not just a technical step in a data cleaning process but a key topic in many fields such as fraudulent document detection, in medical applications and assisted diagnosis systems or detecting security threats. In contrast to population-based methods, neighborhood based local approaches are simple flexible methods that have the potential to perform well in small sample size unbalanced problems. However, a main concern of local approaches is the impact that the computation of each sample neighborhood has on the method performance. Most approaches use a distance in the feature space to define a single neighborhood that requires careful selection of several parameters. This work presents a local approach based on a local measure of the heterogeneity of sample labels in the feature space considered as a topological manifold. Topology is computed using the communities of a weighted graph codifying mutual nearest neighbors in the feature space. This way, we provide with a set of multiple neighborhoods able to describe the structure of complex spaces without parameter fine tuning. The extensive experiments on real-world data sets show that our approach overall outperforms, both, local and global strategies in multi and single view settings.

Outlier, or anomaly, detection is essential for optimal performance of machine learning methods and statistical predictive models. It is not just a technical step in a data cleaning process but a key topic in many fields such as fraudulent document detection, in medical applications and assisted diagnosis systems or detecting security threats. In contrast to population-based methods, neighborhood based local approaches are simple flexible methods that have the potential to perform well in small sample size unbalanced problems. However, a main concern of local approaches is the impact that the computation of each sample neighborhood has on the method performance. Most approaches use a distance in the feature space to define a single neighborhood that requires careful selection of several parameters. This work presents a local approach based on a local measure of the heterogeneity of sample labels in the feature space considered as a topological manifold. Topology is computed using the communities of a weighted graph codifying mutual nearest neighbors in the feature space. This way, we provide with a set of multiple neighborhoods able to describe the structure of complex spaces without parameter fine tuning. The extensive experiments on real-world data sets show that our approach overall outperforms, both, local and global strategies in multi and single view settings.

Anomaly detection is referred to as a process in which the aim is to detect data points that follow a different pattern from the majority of data points. Anomaly detection methods suffer from several wellknown challenges that hinder their performance such as high dimensionality. Autoencoders are unsupervised neural networks that have been used for the purpose of reducing dimensionality and also detecting network anomalies in large datasets. The performance of autoencoders debilitates when the training set contains noise and anomalies. In this paper, a new gradient-reversal method is proposed to overcome the influence of anomalies on the training phase for the purpose of detecting network anomalies. The method is different from other approaches as it does not require an anomaly-free training set and is based on reconstruction error. Once latent variables are extracted from the network, Local Outlier Factor is used to separate normal data points from anomalies. A simple pruning approach and data augmentation is also added to further improve performance. The experimental results show that the proposed model can outperform other wellknow approaches.

The increased use of real-time water quality monitoring using automated systems with sensors demands and makes it possible to identify unexpected values in time. Anomalies are brought by technical issues that are likely to prevent detection of problematic data manually at the incoming data rate. Use of machine learning approaches to detect anomalies for water quality data is the main focus of this article. There is analysis of four time series machine learning anomaly detection techniques: the local outlier factor, the isolation forest, the extended isolation forest and robust random cut forest. A subset data collected from deployment of sensors in a water treatment plant (Nyeri-Kenya) was used to carry out extensive analysis of experiments of the afore-mentioned techniques; for turbidity and pH parameters. There was successful correct detection of all outliers for both subsets by the local outlier factor algorithm, contrary to the rest of the other algorithms considered. As per the primary experiment, the local outlier factor emerged the fastest. Also, it was easier use as long as there was selection of optimum parameters. Moreover, analysis of the four techniques demonstrated that with or without training, it is a powerful tool for water quality anomaly detection and hence a feasible approach.

The increased use of real-time water quality monitoring using automated systems with sensors demands and makes it possible to identify unexpected values in time. Anomalies are brought by technical issues that are likely to prevent detection of problematic data manually at the incoming data rate. Use of machine learning approaches to detect anomalies for water quality data is the main focus of this article. There is analysis of four time series machine learning anomaly detection techniques: the local outlier factor, the isolation forest, the extended isolation forest and robust random cut forest. A subset data collected from deployment of sensors in a water treatment plant (Nyeri-Kenya) was used to carry out extensive analysis of experiments of the afore-mentioned techniques; for turbidity and pH parameters. There was successful correct detection of all outliers for both subsets by the local outlier factor algorithm, contrary to the rest of the other algorithms considered. As per the primary experiment, the local outlier factor emerged the fastest. Also, it was easier use as long as there was selection of optimum parameters. Moreover, analysis of the four techniques demonstrated that with or without training, it is a powerful tool for water quality anomaly detection and hence a feasible approach.

Detection of anomalies (outliers or abnormal instances) is an important element in a range of applications such as fault, fraud, suspicious behavior detection and knowledge discovery. In this article we propose a new method for anomaly detection and performed tested its ability to detect anomalous behavior in videos from DARPA's Mind's Eye program, containing a variety of human activities. In this semi-unsupervised task a set of normal instances is provided for training, after which unknown abnormal behavior has to be detected in a test set. The features extracted from the video data have high dimensionality, are sparse and inhomogeneously distributed in the feature space making it a challenging task. Given these characteristics a distance-based method is preferred, but choosing a threshold to classify instances as (ab)normal is non-trivial. Our novel aproach, the Adaptive Outlier Distance (AOD) is able to detect outliers in these conditions based on local distance ratios. The underlying assumption is that the local maximum distance between labeled examples is a good indicator of the variation in that neighborhood, and therefore a local threshold will result in more robust outlier detection. We compare our method to existing state-of-art methods such as the Local Outlier Factor (LOF) and the Local Distance-based Outlier Factor (LDOF). The results of the experiments show that our novel approach improves the quality of the anomaly detection.

Let G be a bounded simply-connected domain in the complex plane C, whose boundary Γ := ∂G is a Jordan curve, and let {pn} ∞ n=0 denote the sequence of Bergman polynomials of G. This is defined as the sequence of polynomials that are orthonormal with respect to the inner product where dA stands for the area measure. The purpose of this note is to report on recent results regarding the fine asymptotic behaviour of the the leading coefficients λn, n ∈ N, and the polynomials pn(z), for z ∈ Ω := C \\ (G), in cases when the boundary Γ contains corners. These results complement an investigation started in the 1920's by T. Carleman, who obtained the fine asymptotics for domains with analytic boundaries and carried over by P.K. Suetin in the 1960's, who established them for domains with smooth boundaries.

Let G be a bounded simply-connected domain in the complex plane C, whose boundary Γ := ∂ G is a Jordan curve, and let {p n } ∞ n=0 denote the sequence of Bergman polynomials of G. This is defined as the sequence of polynomials that are orthonormal with respect to the inner product f , g := G f (z)g(z) d A(z), where dA stands for the area measure. The aim of this Note is to report on results regarding the strong asymptotics of p n and λ n , n ∈ N, under the assumption that Γ is piecewise analytic. These results complement an investigation started in 1923 by T. Carleman, who derived the strong asymptotics for domains with analytic boundaries and carried over by P.K. Suetin in the 1960's, who established them for domains with smooth boundaries.

Random Projection (RP) is a popular and efficient technique to preprocess high-dimensional data and to reduce its dimensionality. While RP has been widely used and evaluated in stationary data analysis scenarios, non-stationary environments are not well analyzed. In this paper we provide a profound evaluation of RP on streaming data. We discuss how RP can be bounded for streaming data using the Johnson-Lindenstrauss (JL) lemma. In particular we analyze the effect of concept drift, as a key challenge for streaming data. We also provide experiments with RP on streaming data, using state-of-the-art streaming classifiers like Adaptive Hoeffding Tree, to evaluate its efficiency.

Random Projection (RP) is a popular and efficient technique to preprocess high-dimensional data and to reduce its dimensionality. While RP has been widely used and evaluated in stationary data analysis scenarios, non-stationary environments are not well analyzed. In this paper we provide a profound evaluation of RP on streaming data. We discuss how RP can be bounded for streaming data using the Johnson-Lindenstrauss (JL) lemma. In particular we analyze the effect of concept drift, as a key challenge for streaming data. We also provide experiments with RP on streaming data, using state-of-the-art streaming classifiers like Adaptive Hoeffding Tree, to evaluate its efficiency.

An outlier ranking tree selection approach to extreme pruning of random forests. In Jayne, C. and Iliadis, L. (eds.) Communications in computer and information science, 629, Engineering applications of neural networks: proceedings of the 17th international conference on engineering applications of neural networks (EANN 2016), 2-5

Due to unavailability of prediction system, the success rate of a liver transplant is subordinate. For optimal organ allocation, MELD score is used which follows the sickest first policy. In sickest first policy, the sickest patient gets transplanted without considering its characteristics. This can sometimes result in transplanting liver to a person who is undeserving instead of the person who is suitable for the liver. Data mining can be a boon to predict the accurate lifespan of the patient. So proposed model uses a learning model powered by convolution neural network which predicts the lifespan of the patient.

Outlier detection (OD) is a key problem, for which numerous solutions have been proposed. To deal with the difficulties associated with outlier detection across various domains and data characteristics, ensembles of outlier detectors have recently been employed to improve the performance of individual outlier detectors. In this paper, we follow an ensemble outlier detection approach in which good outlier detectors are selected through an enhanced clustering-based dynamic selection (CBDS) method. In this method, a bisecting K-means clustering algorithm is employed to partition the input data into clusters where every cluster defines a local region of competence. Among the initial pool of detectors, the outputs of the detectors with the most competent local performance were combined through four possible schemes to produce the final OD results. Experimental evaluation and comparison of our method were carried out against four variants of locally selective combination in parallel (LSCP) outlier ensembles. The CBDS-based schemes compare well with the LSCP-based ones on 16 public benchmark datasets and incur considerably lower computational costs. The CBDS method consistently achieved superior average scores of the area under the curve (AUC) of the receiver operating characteristic (ROC), and particularly outperformed the LSCP method on nine of the 16 datasets in terms of the AUC score. In addition, while the CBDS and LSCP methods have similar computational costs on small datasets, the CBDS method achieves significant time savings compared with the LSCP method on large datasets. INDEX TERMS Bisecting K-means, dynamic detector selection, outlier detection, outlier ensemble.

Random Forest (RF) is an ensemble classification technique that was developed by Breiman over a decade ago. Compared with other ensemble techniques, it has proved its accuracy and superiority. Many researchers, however, believe that there is still room for enhancing and improving its performance in terms of predictive accuracy. This explains why, over the past decade, there have been many extensions of RF where each extension employed a variety of techniques and strategies to improve certain aspect(s) of RF. Since it has been proven empirically that ensembles tend to yield better results when there is a significant diversity among the constituent models, the objective of this paper is twofolds. First, it investigates how an unsupervised learning technique, namely, Local Outlier Factor (LOF) can be used to identify diverse trees in the RF. Second, trees with the highest LOF scores are then used to produce an extension of RF termed LOFB-DRF that is much smaller in size than RF, and yet performs at least as good as RF, but mostly exhibits higher performance in terms of accuracy. The latter refers to a known technique called ensemble pruning. Experimental results on 10 real datasets prove the superiority of our proposed extension over the traditional RF. Unprecedented pruning levels reaching as high as 99% have been achieved at the time of boosting the predictive accuracy of the ensemble. The notably high pruning level makes the technique a good candidate for real-time applications.

Today, failure modes characterization and early detection is a key issue in complex assets. This is due to the negative impact of corrective operations and the conservative strategies usually put in practice, focused on preventive maintenance. In this paper anomaly detection issue is addressed in new monitoring sensor data by characterizing and modeling operational behaviors. The learning framework is performed on the basis of a machine learning approach that combines constrained K-means clustering for outlier detection and fuzzy modeling of distances to normality. A final score is also calculated over time, considering the membership degree to resulting fuzzy sets and a local outlier factor. Proposed solution is deployed in a CBM+ platform for online monitoring of the assets. In order to show the validity of the approach, experiments have been conducted on real operational faults in an auxiliary marine diesel engine. Experimental results show a fully comprehensive yet accurate prognostics approach, improving detection capabilities and knowledge management. The performance achieved is quite high (precision, sensitivity and specificity above 93% and κ = 0 . 93 ), even more so given that a very small percentage of real faults are present in data.

As machine learning and cybersecurity continue to explode in the context of the digital ecosystem, the complexity of cybersecurity data combined with complicated and evasive machine learning algorithms leads to vast difficulties in designing an end-to-end system for intelligent, automatic anomaly classification. On the other hand, traditional systems use elementary statistics techniques and are often inaccurate, leading to weak centralized data analysis platforms. In this paper, we propose a novel system that addresses these two problems, titled CAMLPAD, for Cybersecurity Autonomous Machine Learning Platform for Anomaly Detection. The CAMLPAD systems streamlined, holistic approach begins with retrieving a multitude of different species of cybersecurity data in realtime using elasticsearch, then running several machine learning algorithms, namely Isolation Forest, Histogram-Based Outlier Score (HBOS), Cluster-Based Local Outlier Factor (CBLOF), and K-Means Clustering, to process the data. Next, the calculated anomalies are visualized using Kibana and are assigned an outlier score, which serves as an indicator for whether an alert should be sent to the system administrator that there are potential anomalies in the network. After comprehensive testing of our platform in a simulated environment, the CAMLPAD system achieved an adjusted rand score of 95 percent, exhibiting the reliable accuracy and precision of the system. All in all, the CAMLPAD system provides an accurate, streamlined approach to real-time cybersecurity anomaly detection, delivering a novel solution that has the potential to revolutionize the cybersecurity sector.

In this paper, the impact of-means and local outliner factor on data set is studied. Outlier is the observation which is different from or inconsistent with the rest of the data. However, the main challenges of outlier detection are increasing complexity due to variety of datasets and size of dataset. To evaluate the outlierness and catch similar outliers as a group are also issues of this technique. The concept of (Local Outlier Factor) is presented in this work. The paper describes comparative study of five different methodologies using-means as the base algorithm along with the various distances method used in finding the dissimilarities between the objects hence to analyze the effects of the outliers on the cluster analysis of dataset in data mining.

We propose a deterministic initialization of the Echo State Network reservoirs to ensure that the activation of its internal echo state representations reflects similar topological qualities of the input signal which should lead to a self-organizing reservoir. Human actions encoded as a multivariate time series signal are clustered before using the clustered nodes and interconnectivity matrices for initializing the S-ConvESN reservoirs. The capability of S-ConvESN is evaluated using several 3Dskeleton-based action recognition datasets.

Outlier, or anomaly, detection is essential for optimal performance of machine learning methods and statistical predictive models. It is not just a technical step in a data cleaning process but a key topic in many fields such as fraudulent document detection, in medical applications and assisted diagnosis systems or detecting security threats. In contrast to population-based methods, neighborhood based local approaches are simple flexible methods that have the potential to perform well in small sample size unbalanced problems. However, a main concern of local approaches is the impact that the computation of each sample neighborhood has on the method performance. Most approaches use a distance in the feature space to define a single neighborhood that requires careful selection of several parameters. This work presents a local approach based on a local measure of the heterogeneity of sample labels in the feature space considered as a topological manifold. Topology is computed using the communities of a weighted graph codifying mutual nearest neighbors in the feature space. This way, we provide with a set of multiple neighborhoods able to describe the structure of complex spaces without parameter fine tuning. The extensive experiments on real-world data sets show that our approach overall outperforms, both, local and global strategies in multi and single view settings.

Outlier detection (OD) is a key problem, for which numerous solutions have been proposed. To deal with the difficulties associated with outlier detection across various domains and data characteristics, ensembles of outlier detectors have recently been employed to improve the performance of individual outlier detectors. In this paper, we follow an ensemble outlier detection approach in which good outlier detectors are selected through an enhanced clustering-based dynamic selection (CBDS) method. In this method, a bisecting K-means clustering algorithm is employed to partition the input data into clusters where every cluster defines a local region of competence. Among the initial pool of detectors, the outputs of the detectors with the most competent local performance were combined through four possible schemes to produce the final OD results. Experimental evaluation and comparison of our method were carried out against four variants of locally selective combination in parallel (LSCP) outlier ensembles. The CBDS-based schemes compare well with the LSCP-based ones on 16 public benchmark datasets and incur considerably lower computational costs. The CBDS method consistently achieved superior average scores of the area under the curve (AUC) of the receiver operating characteristic (ROC), and particularly outperformed the LSCP method on nine of the 16 datasets in terms of the AUC score. In addition, while the CBDS and LSCP methods have similar computational costs on small datasets, the CBDS method achieves significant time savings compared with the LSCP method on large datasets. INDEX TERMS Bisecting K-means, dynamic detector selection, outlier detection, outlier ensemble.

Growing interest in data and analytics in education, teaching, and learning raises the priority for increased, high-quality research Data Mining is a technique used to find out possibly new information from huge amount of data. Educational data mining is an emerging trend, concerned with developing methods for exploring the huge data that come from the educational system. . The objective of this research is to introduce Educational Data mining, by describing a step-by-step process using a variety of techniques. In this paper a review is conducted on step by step processes and application areas.

Outlier Detection is a Data Mining Application. Outlier contains noisy data which is researched in various domains. The various techniques are already being researched that is more generic. We surveyed on various techniques and applications of outlier detection that provides a novel approach that is more useful for the beginners. The proposed approach helps to clean data at university level in less time with great accuracy. This survey includes the existing outlier techniques and applications where the noisy data exists. Our paper defines critical review on various techniques used in different applications of outlier detection that are to be researched further and they gives a particular type of knowledge based data i.e. more useful in research activities. So where the Anomalies is present it will be detected through outlier detection techniques and monitored accordingly especially in educational Data Mining.

This paper proposes a novel incremental modification to the Local Outlier Probabilities algorithm, which is commonly used for anomaly detection, to allow it to detect outliers nearly instantly in data streams. The proposed incremental algorithm's strength is based on denying the insertion of incremental points into the data set. This precludes the anomaly scores of other points having to update (saving valuable computational time) while resulting in a small amount of error, as compared to an exact approach. This work aims to allow low-resource machines, such as small or older satellites, to perform incremental anomaly detection on large static data sets quickly, trading accuracy impairment for speed of detection.

Internet of things (IoT) becomes the most popular term in the recent advances in Healthcare devices. The healthcare data in the IoT process and structure is very sensitive and critical in terms of healthy and technical considerations. Outlier detection approaches are considered as principal tool or stage of any IoT system and are mainly categorized in statistical and probabilistic, clustering and classification-based outlier detection. Recently, fuzzy logic (FL) system is used in ensemble and cascade systems with other ML-based tools to enhance outlier detection performance but its limitation involves the false detection of outliers. In this paper, we propose a fuzzy logic system that uses the anomaly score of each point using local outlier factor (LOF), connectivity-based outlier factor (COF) and generalized LOF to eliminate the confusion in classifying points as outliers or inliers. Regarding human activity recognition (HAR) dataset, the FL achieved a value of 98.2 %. Compared to ...

Wind energy integration research generally relies on complex sensors located at remote sites. The procedure for generating high-level synthetic information from databases containing large amounts of lowlevel data must therefore account for possible sensor failures and imperfect input data. The data input is highly sensitive to data quality. To address this problem, this paper presents an empirical methodology that can efficiently preprocess and filter the raw wind data using only aggregated active power output and the corresponding wind speed value sat the wind farm. First, raw wind data properties are analyzed, and all the data are divided into six categories according to their attribute magnitudes from a statistical perspective. Next, the weighted distance, a novel concept of the degree of similarity between the individual objects in the wind database and the local outlier factor (LOF) algorithm is incorporated to compute the outlier factor of every individual object, and this outlier factor is then used to assess which category an object belongs to.

Outlier detection (OD) is a key problem, for which numerous solutions have been proposed. To deal with the difficulties associated with outlier detection across various domains and data characteristics, ensembles of outlier detectors have recently been employed to improve the performance of individual outlier detectors. In this paper, we follow an ensemble outlier detection approach in which good outlier detectors are selected through an enhanced clustering-based dynamic selection (CBDS) method. In this method, a bisecting K-means clustering algorithm is employed to partition the input data into clusters where every cluster defines a local region of competence. Among the initial pool of detectors, the outputs of the detectors with the most competent local performance were combined through four possible schemes to produce the final OD results. Experimental evaluation and comparison of our method were carried out against four variants of locally selective combination in parallel (LSCP) outlier ensembles. The CBDS-based schemes compare well with the LSCP-based ones on 16 public benchmark datasets and incur considerably lower computational costs. The CBDS method consistently achieved superior average scores of the area under the curve (AUC) of the receiver operating characteristic (ROC), and particularly outperformed the LSCP method on nine of the 16 datasets in terms of the AUC score. In addition, while the CBDS and LSCP methods have similar computational costs on small datasets, the CBDS method achieves significant time savings compared with the LSCP method on large datasets. INDEX TERMS Bisecting K-means, dynamic detector selection, outlier detection, outlier ensemble.

Internet of things (IoT) becomes the most popular term in the recent advances in Healthcare devices. The healthcare data in the IoT process and structure is very sensitive and critical in terms of healthy and technical considerations. Outlier detection approaches are considered as principal tool or stage of any IoT system and are mainly categorized in statistical and probabilistic, clustering and classification-based outlier detection. Recently, fuzzy logic (FL) system is used in ensemble and cascade systems with other ML-based tools to enhance outlier detection performance but its limitation involves the false detection of outliers. In this paper, we propose a fuzzy logic system that uses the anomaly score of each point using local outlier factor (LOF), connectivity-based outlier factor (COF) and generalized LOF to eliminate the confusion in classifying points as outliers or inliers. Regarding human activity recognition (HAR) dataset, the FL achieved a value of 98.2 %. Compared to ...

Statistical re-sampling techniques have been used extensively and successfully in the machine learning approaches for generation of classifier and predictor ensembles. It has been frequently shown that combining so called unstable predictors has a stabilizing effect on and improves the performance of the prediction system generated in this way. In this paper we use the resampling techniques in the context of Principal Component Analysis (PCA). We show that the proposed PCA ensembles exhibit a much more robust behaviour in the presence of outliers which can seriously affect the performance of an individual PCA algorithm. The performance and characteristics of the proposed approaches are illustrated on a number of experimental studies where an individual PCA is compared to the introduced PCA ensemble.

This article investigates the effects of outliers on the coefficient of determination, R2 which is computed by Ordinary Least Squares (OLS) estimator. It is now evident that the OLS is greatly affected by outliers and hence the R2 is also affected. This problem can be solved by using the robust estimators such as Least Trimmed Squares (LTS) estimator. In this article, we compare the value of R2 which is computed by OLS and LTS estimators. We modify a regression data set to effectively generate outliers in both X and Y directions. Then the coefficient of determination (OLS and LTS) is investigated from the modified data sets (data with outliers). The numerical results show the merit of using the LTS based R2 estimator compared to the OLS estimator.

Outlier detection (OD) is a key problem, for which numerous solutions have been proposed. To deal with the difficulties associated with outlier detection across various domains and data characteristics, ensembles of outlier detectors have recently been employed to improve the performance of individual outlier detectors. In this paper, we follow an ensemble outlier detection approach in which good outlier detectors are selected through an enhanced clustering-based dynamic selection (CBDS) method. In this method, a bisecting K-means clustering algorithm is employed to partition the input data into clusters where every cluster defines a local region of competence. Among the initial pool of detectors, the outputs of the detectors with the most competent local performance were combined through four possible schemes to produce the final OD results. Experimental evaluation and comparison of our method were carried out against four variants of locally selective combination in parallel (LSCP) outlier ensembles. The CBDS-based schemes compare well with the LSCP-based ones on 16 public benchmark datasets and incur considerably lower computational costs. The CBDS method consistently achieved superior average scores of the area under the curve (AUC) of the receiver operating characteristic (ROC), and particularly outperformed the LSCP method on nine of the 16 datasets in terms of the AUC score. In addition, while the CBDS and LSCP methods have similar computational costs on small datasets, the CBDS method achieves significant time savings compared with the LSCP method on large datasets. INDEX TERMS Bisecting K-means, dynamic detector selection, outlier detection, outlier ensemble.

Internet of things (IoT) becomes the most popular term in the recent advances in Healthcare devices. The healthcare data in the IoT process and structure is very sensitive and critical in terms of healthy and technical considerations. Outlier detection approaches are considered as principal tool or stage of any IoT system and are mainly categorized in statistical and probabilistic, clustering and classification-based outlier detection. Recently, fuzzy logic (FL) system is used in ensemble and cascade systems with other ML-based tools to enhance outlier detection performance but its limitation involves the false detection of outliers. In this paper, we propose a fuzzy logic system that uses the anomaly score of each point using local outlier factor (LOF), connectivity-based outlier factor (COF) and generalized LOF to eliminate the confusion in classifying points as outliers or inliers. Regarding human activity recognition (HAR) dataset, the FL achieved a value of 98.2 %. Compared to ...

In this paper, a novel method for detecting transformer winding axial displacement has been presented. In this method, which is based on UWB radar imaging, a UWB pulse is transmitted to the transformer winding and the reflection from it is received and recorded. By changing the antenna position this process is repeated on several points along the axis of the winding. The measured signals are mapped to a 2-D image of the winding. By analyzing this image, the axial displacement of the winding can detected and the magnitude of it is determined with an acceptable precision. Simulation results are provided to verify the proposed method.

Outlier detection (OD) is a key problem, for which numerous solutions have been proposed. To deal with the difficulties associated with outlier detection across various domains and data characteristics, ensembles of outlier detectors have recently been employed to improve the performance of individual outlier detectors. In this paper, we follow an ensemble outlier detection approach in which good outlier detectors are selected through an enhanced clustering-based dynamic selection (CBDS) method. In this method, a bisecting K-means clustering algorithm is employed to partition the input data into clusters where every cluster defines a local region of competence. Among the initial pool of detectors, the outputs of the detectors with the most competent local performance were combined through four possible schemes to produce the final OD results. Experimental evaluation and comparison of our method were carried out against four variants of locally selective combination in parallel (LSCP) outlier ensembles. The CBDS-based schemes compare well with the LSCP-based ones on 16 public benchmark datasets and incur considerably lower computational costs. The CBDS method consistently achieved superior average scores of the area under the curve (AUC) of the receiver operating characteristic (ROC), and particularly outperformed the LSCP method on nine of the 16 datasets in terms of the AUC score. In addition, while the CBDS and LSCP methods have similar computational costs on small datasets, the CBDS method achieves significant time savings compared with the LSCP method on large datasets. INDEX TERMS Bisecting K-means, dynamic detector selection, outlier detection, outlier ensemble.

This paper investigates the use of an unsupervised hybrid statistical–local outlier factor algorithm to detect anomalies in time-series flight data. Flight data analysis is an activity carried out by airlines primarily as a means of improving the safety and operation of their fleet. Traditionally, this is performed by checking exceedances in pre-set limits to the flight data parameters. However, this method highlights single events during a flight, making this analysis laborious. The process also fails to establish trends or reflect potential unknown hazards. This research took advantage of machine learning techniques to recognize patterns in large datasets by implementing the local outlier factor (LOF). In order to minimize human input, a statistical approach was adopted to establish the threshold value above which the flights are considered to be anomalous and interpret the scores. This paper shows that LOF quantifies the degree of outlier-ness of an outlier rather than binary cat...

In large datasets, identifying exceptional or rare cases with respect to a group of similar cases is considered very significant problem. The traditional problem (Outlier Mining) is to find exception or rare cases in a dataset irrespective of the class label of these cases, they are considered rare events with respect to the whole dataset. In this research, we pose the problem that is Class Outliers Mining and a method to find out those outliers. The general definition of this problem is "given a set of observations with class labels, find those that arouse suspicions, taking into account the class labels". We introduce a novel definition of Outlier that is Class Outlier, and propose the Class Outlier Factor (COF) which measures the degree of being a Class Outlier for a data object. Our work includes a proposal of a new algorithm towards mining of the Class Outliers, presenting experimental results applied on various domains of real world datasets and finally a comparison ...

The main objective of this paper is to design and developed a model of power system transmission lines fault identification using Local Outlier Factor (LOF) technique based on data mining. 9 bus power system and 30 bus power systems overhead transmission line fault of are simulated as a test cases using PowerWorld software and the LOF computations using Matlab software. The proposed model consists of two main steps; the first step is used to determine single line-to-ground (SLG) fault and 3 phase fault. The second step was used to determine line-to-line (LL) fault and double line-to-ground (DLG) fault. The second step is required uninterrupted phase voltage in order to distinguish between LL fault and DLG faults. The proposed model successfully identified asymmetrical faults and symmetrical faults that particular single bus fault.

Our research deals with intelligent decision support systems based on rule-based knowledge bases. Decision support systems use rules ”If a condition, then a decision” as a form of knowledge representation. In the process of inference, which mirrors the process of human reasoning, we look for rules that confirm the facts and thus generate new knowledge. Such rule-based knowledge bases can (and often do) contain outlier rules. Our goal is to find such unusual rules. Thanks to this, we can influence the completeness of the knowledge base by finding unusual rules and asking domain experts to supplement knowledge in a rare area. To enhance the effectiveness of decision support systems, we conducted separate investigations into two distinct methods. The first method involved the utilisation of the Local Outlier Factor (LOF) algorithm in detecting rule outliers, while the second method employed the Self-Organizing Maps (SOM) algorithm for the same purpose. Our experiments not only confirmed the effectiveness of both the LOF and SOM algorithms but also involved comparing the results obtained from both methods. The discovery of outlier rules can aid knowledge engineers and domain experts in knowledge exploration and enhance the completeness of the knowledge base, which is crucial for decision support systems.

The aim of the article is the analysis of using LOF, COF and Kmeans algorithms for outlier detection in rule based knowledge bases. The subject of outlier mining is very important nowadays. Outliers in rules mean unusual rules which are rare in comparison to others and should be explored further by the domain expert. In the research the authors use the outlier detection methods to find a given (1%, 5%, 10%) number of outliers in rules. Then, they analyze which of seven various quality indices, that they used for all rules and after removing selected outliers, improve the quality of rule clusters. In the experimental stage the authors used six different knowledge bases. The results show that the optimal results were achieved for COF outlier detection algorithm as the one for which, among all analyzed quality indices, the cluster quality improved most frequently.

The problem of outlier detection in univariate circular data was the object of increased interest over the last decade. New numerical and graphical methods were developed for samples from different circular probability distributions. The main drawback of the existing methods is, however, that they are distribution-based and ignore the problem of multiple outliers. The local outlier factor (LOF) is a density-based method for detecting outliers in multivariate data and it depends on the local density of every k nearest neighbours. The aim of this paper is to extend the application of the LOF to the detection of possible outliers in circular samples, where the angles of circular data are represented in two Cartesian coordinates and treated as bivariate data. The performance of the LOF is compared against other existing numerical methods by means of a simulation based on the power of a test and the proportion of correct detection. The LOF performance is compatible with the best existing discordancy tests, while outperforming other tests. The level of the LOF performance is directly related to the contamination and concentration parameters, while having an inverse relationship with the sample size. In order to illustrate the process, the LOF and other existing discordancy tests are applied to detect possible outliers in two common real circular datasets.

The detection of outliers in text documents is a highly challenging task, primarily due to the unstructured nature of documents and the curse of dimensionality. Text document outliers refer to text data that deviates from the text found in other documents belonging to the same category. Mining text document outliers has wide applications in various domains, including spam email identification, digital libraries, medical archives, enhancing the performance of web search engines, and cleaning corpora used in document classification. To address the issue of dimensionality, it is crucial to employ feature selection techniques that reduce the large number of features without compromising their representativeness of the domain. In this paper, we propose a hybrid density-based approach that incorporates mutual information for text document outlier detection. The proposed approach utilizes normalized mutual information to identify the most distinct features that characterize the target doma...

One of the most significant security concerns confronting network technology is the detection of distributed denial of service (DDOS). This paper introduces a semi-supervised datadriven approach to the detection of DDOS attacks. The proposed method employs normal events data without labeling to train the detection model. Specifically, this approach introduces an improved autoencoder (AE) model by incorporating a Gated Recurrent Unit (GRU) based on the attention mechanism (AM) at the encoder and decoder sides of the AE model. GRU enhances the AE's ability to learn temporal dependencies, and the AM enables the selection of relevant features. For DDOS attacks detection, the local outlier factor (LOF) anomaly detection algorithm is applied to extracted features from the improved AE model. The performance of the proposed approach has been verified using DDOS publically available datasets.

Detecting anomalies over real-world datasets remains a challenging task. Data annotation is an intensive human labor problem, particularly in sequential datasets, where the start and end time of anomalies are not known. As a result, data collected from sequential real-world processes can be largely unlabeled or contain inaccurate labels. These characteristics challenge the application of anomaly detection techniques based on supervised learning. In contrast, Multiple Instance Learning (MIL) has been shown effective on problems with incomplete knowledge of labels in the training dataset, mainly due to the notion of bags. While largely under-leveraged for anomaly detection, MIL provides an appealing formulation for anomaly detection over real-world datasets, and it is the primary contribution of this paper. In this paper, we propose an MIL-based formulation and various algorithmic instantiations of this framework based on different design decisions for key components of the framework. We evaluate the resulting algorithms over four datasets that capture different physical processes along different modalities. The experimental evaluation draws out several observations. The MIL-based formulation performs no worse than single instance learning on easy to moderate datasets and outperforms single-instance learning on more challenging datasets. Altogether, the results show that the framework generalizes well over diverse datasets resulting from different real-world application domains.